Pyc3704 Question and Answer or Memo

PYC3704 Psychological Research
Exam Questions and Answers
written by
adeles
The study-notes marketplace
Buy and sell all your summaries, notes, theses, essays, papers, cases, manuals, researches, and
many more...
www.stuvia.co.za
Downloaded by: maestrofusa | maestrofusa@gmail.com

Distribution of this document is illegal
Stuvia.com - The study-notes marketplace
1 PYC3704 Psychological Research
This document is a compilation of UNISA Exam Questions and Answers
Answers are motivated by a combination of:
• Short summaries/reasoning regarding the relevant topic(s) in question. (Incorrect options

are also marked where applicable, in order to identify and disregard red-herring alternatives)
Exams covered are:
• 2016 May-June
• 2016 October-November
• 2017 May-June
• 2017 October November
• Mock Exam 1
• Mock Exam 2
• Test yourself Questions and Answers from the Study Guide
Please note: This document is an additional tool for exam preparation. The Stuvia-user that compiled
and uploaded this document takes no responsibility for incorrect answers. Students must ensure
that they study the prescribed material and understand the content.

May June 2016

Question 1
A theory can be described as an interdependent set of - - - - - relations between - - - - -
1. proposed, constructs
2. empirical, hypotheses
3. verified, variables
Answer: The correct option is 1

Reasoning:
• Alternative 1 is correct because a theory is defined as a “network of postulated relations
between constructs”.
• Alternative 2 is wrong because one does not test relations between hypotheses, but
between variables.
• The relations are postulated (and therefore not verified) so that alternative 3 is also
incorrect.
Question 2
A measurement model of attention deficit disorder relates this - - - - - to its - - - - -
1. construct, intervening variables

2. hypothetical variable, observable instances
3. variable, parameters

Reasoning:
• Alternative 2 is correct because (a) ‘attention deficit disorder’ is a hypothetical variable
used to refer to a cluster of observable symptoms, and (b) the symptoms are the
observable instances (of behaviour) which are used to measure (e.g. indicate the severity)
of the disorder.
• Alternative 1 is incorrect because one requires manifest, not latent variables for
measurement.
• Alternative 3 is also incorrect because a model is not a variable, but a theory of the
relationship between ‘referents’ (or hypothetical entities).
Use the following scenario to answer Questions 3 to 5
"Acute stress disorder among patients who suffer from this disorder can be explained in terms of how
the intensity of stress is affected by personality factors, by the nature of the stressors which they
experience, and by the support they experience in their social system. My research will investigate
whether the level of anxiety of these patients can be reduced by providing social support through
group therapy. More specifically, patients receiving group therapy are expected to score lower on the
Manifest Anxiety Scale than patients not receiving therapy"
Question 3
"Acute stress disorder among patients who suffer from this disorder can be explained in terms of
how the intensity of stress is affected by personality factors, by the nature of the stressors which
they experience, and by the support they experience in their social system” is a(n) - - - --

1. hypothesis
2. theory
3. operational definition
Question 4
The dependent variable(s) in my research is/are - - - - -
1. personality factors, nature of stressors, support received

2. whether or not group therapy is received
3. level of anxiety experienced by patients

Reasoning:
In the hypothesis it is indicated the level or intensity of anxiety experienced ‘depends’ on other
variables such as personality factors, the nature of the stressors and support experienced in the
social system, showing that it functions as a dependent or Y-variable which is to be predicted or
explained in the study.
[The dependent variable is usually the one that the researcher is interested in, the variable that is
the focus of the research. The independent variable is something that the researcher manipulates,
to see how this affects the dependent variable (in other words, the dependent variable is
dependent on the independent variable).]
Question 5
When interpreting the results of this research I will assume that personality factors and the nature of
the stressors - - - - -
1. do affect level of anxiety, but their effects more or less cancel out over all my patients in the
research sample
2. do not affect level of anxiety
3. do affect level of anxiety, but according to the central limit theorem their average effect will
be zero

Reasoning:
• Alternative 1 is correct because it is obvious that the type of stressor may have an effect
on the level of anxiety experienced, but if an unbiased (e.g. random) sample is selected
from the population, the influence of the type of stressor will be averaged over the
sample.
• Alternative 2 is incorrect because there are no grounds for assuming that the type of
stressor will not affect anxiety.
• Alternative 3 is also incorrect because the central limit theory is not applicable here (it
refers to the nature of the sampling distributions of sampling statistics and not to the
value of specific variables).

Question 6
A psychologist conducts a study in which she measures the reaction times of students doing a
psychometric test. She proceeds from the assumption that a fast reaction time is a good indication
of high intelligence. In this study 'intelligence' is the - - - - - variable
1. operational
2. latent
3. manifest

Reasoning:
Intelligence is a latent variable because it cannot be observed directly. The results of the
psychometric test can however be observed directly and can therefore be regarded as the
manifest variable.
Use the following scenario to answer Questions 7 and 8
Jeff's explanation of size perception in the natural environment states that the estimated size of a
distant object is affected by its true size, distance from the observer, and transparency of the
atmosphere. He decides to investigate whether the claim that estimated size increases with haziness
is valid.
Question 7
The statement "estimated size increases with haziness" represents the - - - - -
1. observed relation between two variables

2. research hypothesis

Reasoning:
• Alternative 2 is correct, because a specific hypothesis is now derived from the theory
presented in the scenario.
• Alternatives 1 and 3 is incorrect because the terms ‘estimated size’ and ‘haziness’ have
not been operationally defined in the statement given.
Question 8
The dependent variable(s) in Jeff's research is/are - - - --
1. true size, distance from the observer, and transparency of the atmosphere
2. haziness
3. estimated size

Reasoning:
(The dependent variable is usually the one that the researcher is interested in, the variable that is
the focus of the research. The independent variable is something that the researcher manipulates,
to see how this affects the dependent variable (in other words, the dependent variable is
dependent on the independent variable).)

In the hypothesis mentioned it is indicated the estimated size ‘depends’ on other variables such as
true size, distance from the observer, and transparency of the atmosphere, showing that it
functions as a dependent or Y-variable which is to be predicted or explained in the study.
Question 9
In a study, the relationship between level of physiological arousal (high and low) and mood
(measured on three levels) is considered. A suitable hypothesis for the study can be viewed as a - - - -
1. rule associating the values of 'physiological arousal' with the values of 'mood'
2. correlation between the constants 'physiological arousal' and 'mood'
3. procedure to make it possible to measure the values of the variables 'physiological arousal'
and 'mood'

Reasoning:
A hypothesis can be informally described as an educated guess. The research hypothesis
expresses the problem in terms of very specific relationships among constructs that we expect to
find (if our guess is true).
It is important that this possible relationship should be clear and unambiguous. A hypothesis that
is stated clearly and specifies exactly what is to be observed and what should be true if it is valid,
is often called an operational hypothesis.
A research hypothesis: a statement about a possible relationship among constructs that may
explain some set of observations that one intends to investigate.
Option 2 is incorrect, as physiological arousal and mood are not constants, but variables.
Question 10
Assume that a researcher believes that education plays a role in promotion. He intends to
investigate this on a sample of workers at Computer Solutions Inc. Which one of the following is the
most appropriate statement of the operational hypothesis?
1. Education is relevant to the promotion of employees at Computer Solutions Inc

2. Employees with higher levels of education earn more than employees with lower levels of
education at Computer Solutions Inc
3. Employees with higher levels of education are more likely to be promoted at Computer
Solutions Inc than employees with lower education at corresponding post levels

Reasoning:
A hypothesis that is stated clearly and specifies exactly what is to be observed and what should be
true if it is valid, is often called an operational hypothesis.
• Alternative 1 is not stated clearly, and therefore incorrect.
• Alternative 2 is also more vague than alternative 3, and relates to earnings, not
promotions.

Question 11
A standard normal distribution has a standard deviation of - - - - - and a mean of - - - --
1. 0, 1
2. 1, 0
3. 1, 10

Reasoning:
A standard normal distribution has a mean of 0 and a standard deviation of 1.
Question 12
Consider the hypothesis:
There is a relationship between self-esteem and eating disorders. People with low self-esteem are
more likely to have eating disorders because they tend to have less healthy eating habits than people
with high self-esteem.
Suppose that µhs indicates be the average of a measurement on a scale that measures 'healthy
eating patterns' (where a higher score means a person exhibits more healthy eating habits), for
people with high self-esteem, and µls, the average eating pattern score for people with low self-
esteem. Which of the following is an appropriate way to state the hypothesis in symbolic form?
1. µhs ≠ µls
2. µhs > µls
3. µhs < µls
Question 13
Which of the options represents a valid description of the law of large numbers?
1. As repetitions of a probability experiment increases, the relative frequency or proportion of

outcomes will approximate the most probable outcome or theoretical probability
2. All probability distributions approach the normal distribution as the sample size increases
3. For a random sample of size n selected from a population with mean µ and standard
deviation σ, the sampling distribution of means obtained from all possible samples is
approximately normal with mean µ and standard deviation σ/√𝑛

Reasoning:
Alternatives 2 and 3 refer to the central limit theorem, and not to the law of large numbers and is
therefore incorrect.
Law of large numbers: If an experiment is done repeatedly, and if the outcomes are independent
of one another, the observed proportion of favourable occurrences of an event will eventually
approach its theoretical probability.

Question 14
Suppose that over the years 10 000 students wrote an examination in a specific course, and that
6400 of them passed, of which 200 obtained exactly 50%. This means that for randomly selected
students the probability of obtaining exactly 50% is - - - - - while the probability of obtaining 50% or
more is - - - - -
1. 0.64, 0.02
2. 0.05, 0.64
3. 0.02, 0.64

Reasoning:
Therefore:
200
• the probability for students obtaining exactly 50% = = 0.02
10 000
6 400
• the probability for students obtaining 50 % or more (a pass) = = 0.64
10 000
Question 15
During the interpretation of psychological measurements, the normal distribution is often - - - - -
1. adapted to fit the observed frequency distribution of scores

2. used as a theoretical model for interpreting the observed distribution of scores
3. used to calculate the relative frequency of observed scores

Reasoning:
The normal distribution is a theoretical distribution which is used to determine the probability of a
given score provided the mean and standard deviation are known.
It is not dependent on observed frequencies (alternative 1), nor is it used to calculate the relative
frequency of observed scores (alternative 3) which can only be obtained empirically.
Question 16
Joseph scores 62% in a History test (class mean 60%, standard deviation 10%) and 54% in a Biology
test (class mean 60%, standard deviation 12%). Use z-scores to decide which statement is true.
Relative to the rest of his class Joseph does - - - - -
1. better in History that in Biology

2. better in Biology than in History
3. equally well in History and Biology

Reasoning:
Joseph’s z-score for History is (62-60)/10 = 0,2, and for Biology it is (54-60)/12 = -0,5.

Question 17
A frequency distribution of the ages in months of a class of Grade 1 children indicates for each - - - -
what the corresponding - - - - - is
1. frequency, age in months

2. age in months, number of children of that age
3. age in months, relative frequency at that age

Reasoning:
A frequency distribution will represent the number of students falling under each age group.
Base your answers to Questions 18 and 19 on the following scenario
A researcher is investigating job satisfaction of workers at a branch office of a particular company.

The distribution of staff at this office is as follows
Managerial Section 5
Administrative Section 15
Technical Section 10
Human Resources Section 6
In order to conduct an interview, the researcher draws the name of a staff member at random
Question 18
What is the probability that the person selected would be in the Administration Section?
1. 0.07
2. 0.42
3. 0.25

Reasoning:
15
Therefore, p = = 0.42
36
Question 19
What is the probability that a worker whose name is selected at random is from the Managerial
Section or from the Human Resources Section?
1. 0.31
2. 0.06
3. 0.4

Reasoning: Since these are mutually exclusive possibilities, we can apply the additive rule directly.
p(Managerial OR Human Resources) = p(Managerial) + p(Human Resources)
𝑛𝑢𝑚𝑏𝑒𝑟 𝑀𝑎𝑛𝑎𝑔𝑒𝑟𝑖𝑎𝑙 𝑛𝑢𝑚𝑏𝑒𝑟 𝐻𝑢𝑚𝑎𝑛 𝑅𝑒𝑠𝑜𝑢𝑟𝑐𝑒𝑠
= +
𝑡𝑜𝑡𝑎𝑙 𝑛𝑢𝑚𝑏𝑒𝑟 𝑡𝑜𝑡𝑎𝑙 𝑛𝑢𝑚𝑏𝑒𝑟
5 6
= +
36 36
5+6
=
36
11
=
36
= 0.305
Question 20
A probability distribution of the ages in months of South African Grade 1 children indicates for each -
- - - - what the corresponding - - - - - is
1. child, age of that child

2. age in months, number of children of that age
3. age in months, probability of a Grade 1 child having that age

Reasoning:
Alternative 2 refers to a frequency distribution, and is therefore incorrect.
(A probability distribution is a mathematical function that, stated in simple terms, can be thought
of as providing the probabilities of occurrence of different possible outcomes in an experiment.)
Question 21
Vusi is conducting research into the ability of people to recognize faces from photographs.
A random sample of research participants are shown a group photo which they are allowed to look
at for ten minutes. Each participant is then shown ten individual photographs, and asked whether
the person on the photo was in the group photo. The table represents a frequency distribution of
the number photos that were identified correctly by the research participants.
Number of correct responses 0 1 2 3 4 5 6 7 8 9 10

Frequency count of participants 0 1 4 11 14 18 22 17 9 6 0
Based on this data, what is the probability be that a person who is selected at random would
correctly identify 7 or more faces from the group photo?
1. 0.07
2. 0.15
3. 0.32


Reasoning:
∑(𝑓𝑟𝑒𝑞𝑢𝑒𝑛𝑐𝑦 𝑐𝑜𝑢𝑛𝑡 𝑜𝑓 𝑐𝑜𝑟𝑟𝑒𝑐𝑡 𝑟𝑒𝑠𝑝𝑜𝑛𝑠𝑒𝑠 7 𝑡𝑜 10)
∑𝑡𝑜𝑡𝑎𝑙 𝑓𝑟𝑒𝑞𝑢𝑒𝑛𝑐𝑦 𝑐𝑜𝑢𝑛𝑡
17+9+6
=
1+4+11+14+18+22+17+9+6
32
=
102
= 0.32
Question 22
John received 55 marks for his psychology test. The average mark for this test is 63, and the standard
deviation is 8. What proportion of the students received higher marks than John?
1. 0.16
2. 0.84
3. 0.34

Reasoning:
John’s z-score is -1. (55-63)/8
Look up the larger portion (higher marks) of this z-score on the z-score table.
= 0.84
Question 23
The asymptotic property of the normal curve refers to the fact that - - - - -
1. the curve is symmetrical and bell-shaped

2. the endpoints of the curve get closer to, but never touch, the horizontal axis
3. the curve represents a distribution of data that was standardized to a mean of 0 and a
standard deviation of 1

Reasoning:
Asymptotic means that the two tails never touch the horizontal axis, moving ever closer to
infinity, because there is always some probability that more extreme values will occur.
Question 24
The central limit theorem states that the - - - - -
1. sampling distribution of a specific variable will approach a normal distribution as the size of
the sample increases
2. sampling error will gradually assume a normal distribution for larger samples
3. distribution of the mean of a large number of samples of a specific variable will be
approximately normal, regardless of the underlying distribution of the variable


Reasoning:
The central limit theorem states that, for a large sample size, the sampling distribution of a mean
is close to normal, irrespective of the shape of the population distribution of the original data.
Question 25
When testing a hypothesis, the p-value represents the probability that we would find the specific
relationship between variables that we see in our measurements, given that the - - - - -
1. null hypothesis is false

2. alternative hypothesis is true
3. null hypothesis is true

Reasoning:
The p-value is an area below the sampling distribution of the statistic (or test statistic). Such a
sampling distribution can only be derived under H0. The p-value represents the probability that
the null hypothesis is true.
Question 26
When a research hypothesis is formally expressed as a statistical hypothesis, it should be expressed

in terms of - - - - -
1. population parameters
2. sample statistics
3. both of the above

Reasoning:
Note that the alternative and null hypotheses here are about the value of μ which of course is a
population parameter.
Question 27
When comparing an observed sample mean with a given population mean, the rejection of H0
implies that a difference between the calculated sample mean and its expected value under H0 is
probably due to-----
1. chance
2. the independent variable
3. sampling error

Reasoning:
The null hypothesis states that the true population mean is i.e. 100, and that any sample deviation
from this - such as a mean of 104 - is due to chance or random sampling error. The p-value is a
probability value that indicates what the chances are that our sample value would be 104 or
greater when it should `really' reflect the population mean of 100, but misses the mark due to
measurement error. Our task is to make up our minds whether we suspect that 104 is probably

due to chance and is, therefore, really an approximation for 100, or whether we believe that 104
is sufficiently higher than 100 to support our alternative hypothesis, in spite of possible
measurement error. If we accept the difference as significant, we would conclude that we can
reject H0 in favour of H1.
Question 28
Suppose we have stated H0 µ = 10, and H1 µ < 10, and find that the sample mean corresponds to a z-
score of -3. This means that the corresponding p-value is equal to - - - - -
1. 0.9987
2. 0.4987
3. 0.0013

Reasoning:
Look up the corresponding ‘smaller portion’ of 3 on the z-score appendix.
Question 29
A researcher wants to determine the effectiveness of an assertiveness training course. She tests a
sample of 200 participants before and after the workshop on a scale which measures assertiveness,
and finds mean scores of ẋ1 = 45 before and ẋ2 = 57 after the workshop. A statistical test shows that
this difference is statistically significant. The scores are however fairly close together and she is
concerned that the result may be due to the relatively large sample size. What can she do to check
whether the result is also fairly important in practical terms? She should - - - - -
1. calculate the power of the test

2. determine the level of significance of the result
3. calculate the effect size

Reasoning:
A major determinant of the sensitivity or power of a statistical test is sample size (which is why we
can increase sample size to enhance power). When the sample is large, even smaller effects will
have statistical significance. One way that statisticians have suggested to deal with this problem is
by the notion of effect size.
Question 30
How is the significance level (α) of a statistical test determined? It is - - - - -
1. looked up in the z-tables

2. selected by the researcher
3. calculated from the test statistic

Reasoning:
The researcher compares the p-value with a level of significance (a) that he/she chose before
he/she did the sampling and made the observation. This is chosen by the researcher, based on the
risk of being wrong when rejecting the null hypothesis that he or she is willing to take.

Question 31
A Type II error occurs when the - - - - -
1. null hypothesis is not rejected when it should be rejected

2. null hypothesis is rejected when it should not be rejected
3. alternative hypothesis is rejected instead of the null hypothesis

Reasoning:
The Type II error of failing to reject a null hypothesis that is really false is indicated by the Greek
symbol β which indicates the probability associated with this risk.
Question 32
When applying a statistical test, we - - - - - the null hypothesis if the p-value is - - - - - or equal to the
level of significance
1. reject, greater
2. accept, smaller
3. reject, smaller

Reasoning:
The null hypothesis is never accepted. The decision regarding the null hypothesis is to reject it or
not to reject it. Therefore alternative 2 is eliminated.
If the p-value is equal to or less than the chosen significance level α, we reject H0 in favour of H1.
Otherwise, do not reject the null hypothesis in favour of the alternative hypothesis.
Base your answers to Questions 33 and 34 on the following hypothesis
"The mean extroversion score on the Eysenck Personality Questionnaire (EPQ) of women who support
abortion is higher than that of women who oppose it”
Question 33
The hypothesis indicates how the constructs - - - - -
1. are operationalized
2. are related
3. differ

Reasoning:
A hypothesis can be informally described as an educated guess. The research hypothesis
expresses the problem in terms of very specific relationships among constructs that we expect to
find (if our guess is true).
It is important that this possible relationship should be clear and unambiguous. A hypothesis that
is stated clearly and specifies exactly what is to be observed and what should be true if it is valid,
is often called an operational hypothesis.

A research hypothesis: a statement about a possible relationship among constructs that may
explain some set of observations that one intends to investigate.
Question 34
The two constructs of importance in the hypothesis are - - - - - and - - - - -
1. gender, personality
2. extroversion, whether a woman supports abortion or not
3. whether abortion is supported or not, gender

Reasoning:
Constructs are:
a) concepts used to account for observations
b) the building blocks of theories
c) hypothetical or theoretical concepts
Question 35
The alternative hypothesis is often a re-statement of the - - - - - hypothesis
1. statistical
2. research
3. null

Reasoning:
A research hypothesis always translates into two mutually exclusive hypotheses (i.e. both cannot
be true at the same time): a null and an alternative hypothesis. Therefore alternative 3 is incorrect
and eliminated.
A statistical hypothesis is the research hypothesis that is written in statistical language. Therefore,
the alternative hypothesis is a statistical hypothesis, and not a “re-statement”.
Question 36
Suppose that the memory span of adults is normally distributed with a mean of 7 items and a
standard deviation of 2 items. A researcher predicts that dyslexic adults have a shorter memory span
than adults in general.
Which of the following is an appropriate alternative hypothesis for testing this prediction?
1. The mean memory span of the population of dyslexic adults is smaller than 7
2. The mean memory span of the population of adults is not equal to 7
3. The mean memory span of the population of dyslexic adults equals 7

Reasoning:
H1: µD < 7
Question 37

If a p-value on a computer printout is reported as '0.0000', what should a researcher assume? It

implies that the value can be interpreted as - - - - -
1. smaller than 0.00001

2. equal to exactly zero
3. too small to calculate

Reasoning:
In statistics, probabilities are sometimes expressed as p = 0.0000. This does not mean p = 0; it is a
convention for indicating that p < 0.00005: i.e., there are at least four zeroes after the decimal
point.
Question 38
Which of the following statement about a null hypothesis is not valid? The null hypothesis is a
statement of what may be expected if - - - - -
1. there are significant relationships among constructs or variables

2. there are no relationships among variables in the research question
3. all relationships among constructs are due to chance or measurement error

Reasoning:
The null hypothesis always contains the èqual to' symbol `='. The null hypothesis is the hypothesis
that no effect exists, and in cases where we are testing a mean, this implies that two group means
(or a group mean and a specific constant value) do not differ.
The probability of obtaining the value that is equal to the value of the null hypothesis purely by
chance, due to random measurement errors, when the null hypothesis is actually true, is referred
to as the p-value.
Question 39
The level of significance is like a - - - - -
1. p-value under H0
2. p-value under H1
3. p-value from the z-tables

Reasoning:
Level of significance ∝ limits the probability of making a Type I error as it sets the maximum
probability.
The p-value represents the probability that the null hypothesis is true: that the effect we see in
our observation is due to chance effects like measurement error. If this probability is small, we
conclude that H0 is not true, and we reject it. This p- value is also a direct indication of the
probability that the null hypothesis is being mistakenly rejected (Type I error).

Question 40
The larger that a value which a researcher chooses as the level of significance is, the greater the
probability of - - - - -
1. a type I error
2. a type II error
3. not rejecting the null hypothesis

Reasoning:
The convention in most research projects is to fix the value of the level of significance (α) in
advance of the actual research, thereby limiting the probability of a Type I error to this value. The
value of a represents the maximum risk that we are willing to take of making a Type I error by
rejecting H0 in error. So, by setting α in advance, and only rejecting H0 if the p-value is smaller
than α, we are protecting ourselves against the probability of making a Type I error of larger than
α.
What if the p-value is not smaller than the a-level and we decide not to reject H0? Now we run the
risk of not rejecting H0 when - in fact - H0 is false and H1 is true. This is referred to as a Type II
error. The decision not to reject H0 is based on the test statistic, from which we determine a p-
value that is not smaller than our chosen level of significance (i.e., p-value > α). However, this
outcome may also be the result of measurement error. The effect may be close to what H0
predicts purely by chance.
This error of failing to reject a null hypothesis that is really false is indicated by the Greek symbol β
(pronounced `beta') which indicates the probability associated with this risk. So, while α indicates
the risk that a researcher is prepared to take of making a Type I error (rejecting H0 when the
researcher should not do so), β is used to indicate the opposite risk - the risk he (or she) is taking
of making a Type II error (not rejecting H0 when in fact he should).
Generally, though, the smaller α, the larger β. If we wish to avoid Type I errors, we set a to a small
value such as 0.01 or even 0.001, but if we want to avoid Type II errors, we could set a to a larger
value.
(Note that option 2 and 3 refers to the same concept, namely a Type II error, both are incorrect,
as there is only one possible answer to a multiple-choice question.)
Question 41
Which of the following symbols is used to indicate the probability of making a Type II error?
1. Alpha or α
2. Beta or β
3. Cohen's d
Question 42
Which one of the following alternative hypotheses would require a one-tailed test of significance?
1. The mean anxiety score for boys differs from the mean score for girls
2. The mean verbal ability score for boys is lower than the mean verbal ability score for girls
3. There is a significant correlation between the test marks for English and marks for
Mathematics for a mixed group of boys and girls


Reasoning:
If the symbol is “≠” then a non-directional (two-tailed) test would be required. Therefore option 1
is incorrect.
Option 3 also does not state <, >, but rather a ≠, therefore this option is eliminated.
(One-tailed = directional)
Question 43
Suppose we want to increase the ability of a statistical test to detect a significant result. Which of
the following options would not be helpful?
1. Increase the sample size

2. Decrease sampling error, measurement error, etc.
3. Set a smaller level of significance

Reasoning:
If a large effect does not yield a significant result, it may be that the statistical test lacks power
(see section 3.3.2) and increasing the sample size will increase the power of the test (i.e. its ability
to detect significant differences).
Question 44
The power of a statistical test indicates the - - - - -
1. sensitivity or 'accuracy' of the test to determine whether an effect exists

2. whether a result is of practical importance, even though it may be significant
3. probability of making a Type I error

Reasoning:
The ability of a statistical test to detect a significant relationship between variables when such a
relationship does in fact exist, is referred to as its power.
This is the inverse of a Type II error: it is the probability of rejecting H0 when, in fact, it is false and
H1 is true. To put it succinctly, it is the probability of correctly rejecting a false null hypothesis.
Therefore option 3 is eliminated.
Question 45
Suppose H0 µ = 100 are tested against H1 µ ≠ 100 at the 0.10 level of significance. If the t-statistic is -
3.20 and the two-tailed p-value is 0.11, what decision regarding the statistical hypothesis should be
taken?
1. Reject H0 and accept H1 at the 0.10 level of significance

2. Reject H1 and accept H0 at the 0.11 level of significance
3. Do not reject H0 at the 0.10 level of significance

Reasoning:
If the p-value is smaller than the level of significance of α = 0.10, it implies that the null hypothesis
can be rejected in favour of the alternative hypothesis.

This p-value is greater than the level of significance, therefore it does not imply that H0 can be
rejected in favour of H1. Option 1 is therefore incorrect.
Option 2 is incorrect, because the decision rule is never to reject H1, we only reject or accept H0.
H1 can only be accepted (once H0 is rejected).
Base your answers to Questions 46 to 49 on the following scenario
An educational psychologist is doing research on numeracy and has drawn a sample of university
students enrolled for research methodology. It is known that the population average on a
psychometric test of Numeracy equals 100, but she believes that the average numeracy level of these
students will be higher than the population average. She sets a level of significance of α = 0.05
Question 46
Select the correct formulation of the hypothesis in this study
1. H0 µ ≠ 100, H1 µ ≥ 100
2. H0 µ = 100, H1 µ ≠ 100
3. H0 µ = 100, H1 µ > 100

Reasoning:
(or a group mean and a specific constant value) do not differ. Therefore alternative 1 is
eliminated. (another reason to eliminate option 1, is the fact that H1 and H0 needs to be mutually
exclusive. ≥ and = is not mutually exclusive.)
Question 47
The hypothesis requires a - - - - - statistical test
1. directional
2. non-directional
3. two-tailed

Reasoning:
Where both values of the mean, either greater than or smaller than 100 are to be considered (H1:
µ ≠ 100), a non-directional or two-tailed test is required.
In this case, the researcher’s hypothesis states that numeracy level is GREATER than (therefore
directional and one-tailed)
Question 48
Suppose the researcher finds after statistical analysis that the average numeracy level in her sample
is 105 with a standard deviation of 8. Which test statistic should she use to see if the difference is
significant?
1. tẋ
2. zẋ
3. tc


Reasoning:
There are 3 types of test statistics, namely tẋ, zẋ and ‫א‬². Therefore alternative 3 is incorrect and
eliminated.
When the standard deviation is known, we use the zẋ test statistic. When the standard deviation
is unknown, we use the tẋ test statistic.
Question 49
The researcher calculates the test statistic, and finds that the p-value associated with the resultant
statistic is 0.062. Based on the scenario above, what conclusion can the researcher make regarding
her hypothesis?
1. The average numeracy of the students is significantly higher than the population average
2. The average numeracy of the students is not significantly higher than the population average
3. The population average differs significantly from the average numeracy of the students

Reasoning:
Using the values given in the scenario and placing them in the formula for zẋ
(ẋ− µ)
zẋ =
𝜎ẋ
Doing arithmetic, we can then see that µ = 104.5
Question 50
Consider the following statistical hypotheses
H0 µ = 60
H1 µ ≠ 60
Suppose the one-tailed p-value is 0.0345 and the level of significance is set at 0.05. The sample mean
was found to be 65. What is the value of the two-tailed or non-directional p-value?
1. 0.10
2. 0.0173
3. 0.0690

Reasoning:
A two-tailed p-value (used in the case of a non-directional hypothesis) is twice the size of a one
tailed p-value (see page 66 of the study guide); or, conversely, a one- tailed p-value (used in the
case of a directional hypothesis) is half the size of a two-tailed probability.
The relationship between one-tailed and two-tailed p-values can be summarized as follows:
• One-tailed p-value = (two-tailed p-value) / 2
• Two-tailed p-value = (one-tailed p-value) x 2

To validate a new depression scale a researcher applies it to 50 patients diagnosed with depression
and 50 patients diagnosed with stress. She predicts that the depression sample will score higher on
the scale (implying more depression) than the stress sample. The mean scores of the two samples are
found to be ẋDEPRESSION = 30 with a standard deviation of 12 for the depression group and ẋSTRESS =
25, with a standard deviation 10 for the stress group.
Question 51
Which is an appropriate alternative hypothesis for the analysis of the results?
1. ẋSTRESS < ẋDEPRESSION

2. µSTRESS ≠ µDEPRESSION
3. µSTRESS > µDEPRESSION
Reasoning:
Option 2 is incorrect on two accounts, it uses a population parameter and it does not show the
direction, (< or >).
Option 3 is also incorrect on two accounts, as it uses a population parameter and it shows the
direction incorrectly, as the hypothesis is that the depression sample will score higher than the
stress sample.
Question 52
What type of statistical test is required?
1. A one-tailed test
2. A two-tailed test
3. A non-directional test

Reasoning:
A directional (one-tailed) test is required.
Question 53
Given the information in the scenario above, which of the following assumptions need to be made
before calculating the test statistic?
1. The population standard deviation is known

2. The two populations have different means
3. The two populations have the same variance

Reasoning:
Option 2 is a given in the scenario, and therefore no need to assume.
Option 3 is incorrect, as the standard deviation for both populations (samples) are given, and no
need to assume.

Question 54
A researcher suspects that the average level of social engagement (need to interact socially) is
higher among females than among males. She wants to test this by comparing the following
hypotheses
H0 µF = µM
H1 µF > µM
where µF indicates the average level of social engagement among females in the population, as
tested on a 7-polnt scale, and µM is the average level of social engagement among males in the
population. She draws random samples of females and males respectively, and calculates the
following mean levels of social engagement scores for each group
Females ẋF = 4.1, Males ẋM = 4.8
What can the researcher infer from these observations?
1. H0 can be rejected
2. H0 cannot be rejected
3. It is necessary to do a t-test to determine whether the difference is significant

Reasoning:
Clearly, the observed value of ẋM is higher than the observed value of ẋF.
This is a difference in the correct direction, which fits with our stated alternative hypothesis. The
question is, however, whether this difference between the scores of 4.1 and 4.8 is statistically
significant, or likely to be just due to chance. Only if it is significant should we have the confidence
to reject the null hypothesis and accept that males have a higher average level of social
engagement.
We can use the t-statistic to determine this.
Question 55
A standard error refers to the extent - - - - -
1. to which sample means are distributed around the actual mean of the sampling distribution
2. to which the sample standard deviation differs from the population standard deviation
3. of the error one would make if you reject the null hypothesis falsely

Reasoning:
We can estimate the size of the error we would make if we used the sample mean as an estimate
of the population mean. This is referred to as the standard error.
Option 3 refers to a Type I error.
Option 2 refers to standard deviation (which together with the mean are the only 2 variables
between the population and the sample), but not to the mean as the definition of standard error
requires.

Question 56
The use of the tc test to compare the means of data from two independent samples of moderate size
is appropriate when - - - - -
a) the samples come from populations that are normally distributed

b) the population variances are equal
1. (b) but not (a)
2. (a) but not (b)
3. (a) and (b)

Reasoning:
Assumptions before using the tc-test:
• Normally distributed with the same standard deviation
• Two samples are independent samples
An educational psychologist wants to know if learners will do significantly better on a test which
measures reasoning skills if they take the same test again. She gives the test to a group of 100 grade
twelve learners, and after an interval of two months she gives the same test to these same learners.
Question 57
What assumption should the educational psychologist make when she tests her hypothesis for
statistical significance?
The samples of measurements from the first and second instances when the test was taken are - - - -
1. not correlated
2. independent
3. dependent

Reasoning:
The same 100 subjects were tested twice – initially and again after two months. In other words,
each subject is matched with himself or herself, which is why the samples are regarded as
dependent. This is a repeated measures design – which is an example of dependent group design.
Question 58
Which test statistic is appropriate to test the difference between the first and second test for
statistical significance?
1. The test statistic based on Pearson's r

2. The td test statistic
3. The tc test statistic

Reasoning:
A tc test is used for independent samples and a td test for dependent or correlated groups.

Question 59
When evaluating a t-test for the comparison of two group means, what does it mean to say, "the
difference between the means of two groups is statistically significant"?
1. If the null hypothesis were true, the results which were found in the sample data would be
unlikely
2. The null hypothesis gives an adequate description of the relationships between the means
3. The results which were found in the sample data would be unlikely if the alternative
hypothesis is true

Reasoning:
If the null hypothesis were true, there would not be a difference between the means of two
groups. Therefore option 2 is incorrect.
The result of statistically significant differences would be unlikely if the null hypothesis is true.
Therefore option 3 is incorrect. (Option 1 and 3 are opposites)
Question 60
A graph which shows the extent to which a measurement of one variable is related to a
measurement on another variable for variables measured on a ratio or interval scale is called a - - - -
1. histogram
2. scatter plot
3. contingency diagram

Reasoning:
Scatter plots represent correlations of variables on a ratio or interval scale, while histograms are
better to represent variables on a nominal or ordinal level.
Question 61
If the relationship between two variables where a person scoring low on one variable is most likely
to score high on the other is determined with a Pearson's correlation coefficient, the value of r is
likely to be
1. higher than zero

2. less than zero
3. close to zero

Reasoning:
A correlation can either be positive or negative. (If no linear relationship exists between two
variables r will be equal to 0. The further r deviates from zero (in either a positive or negative
direction), the stronger is the indication that a linear relationship exists.)
When positive relationships occur, this implies that as one variable gets larger, so does the other.
When negative relationships occur, this implies that as one variable gets larger, the other gets
smaller. (The question relates therefore to a negative relationship)

Question 62
A researcher obtains a correlation coefficient of 0.40 between a test for verbal intelligence and a test
for non-verbal intelligence based on a random sample of 10 people. He decides to confirm his
findings by giving the same two tests to a different random sample of 100 people from the same
population. Once again, he finds that the correlation coefficient is 0.40. Which of these two
calculated correlation coefficients is more likely to differ significantly from zero under the null
hypothesis?
1. That obtained on the larger sample

2. Both are equally likely to be significant
3. That obtained on the smaller sample

Reasoning:
When the sample is large, even smaller effects will have statistical significance. The reason is that
the larger the sample, the less error variance can be expected (variance purely due to
randomness).
The question however asks, “more likely to DIFFER significantly from zero”, indicating a bigger
variance from 0.
Question 63
A researcher wants to establish whether a relationship exists between people's religious affiliation
(out of a list of different religions) and whether they are in favour of or against the death penalty.
Which of the following would be the most appropriate test to use?
1. The t-test for two independent samples

2. Pearson's correlation test statistic
3. The chi-square (‫א‬²( test

Reasoning:
One variable is a nominal level measurement or categorical measurement that is used to indicate
membership of a group (this would be the independent variable), and the other is a measurement
of intensity or quantity on at least an interval level (the dependent variable).
The question is:
Is my dependent variable nominal, ordinal, interval, or ratio?
• If nominal, use chi square
• If ordinal, use chi square
• If interval/ratio, use correlation or t-test

Option 1 is eliminated, as it refers to two independent samples. The same sample is to be used
here, as a correlation between the two variables within the same sample is required.
Question 64
What is the correlation coefficient between the following values of X and Y likely to be?
X 1 1 1 1 1 1
Y -15 0 12 -8 10 0
1. -1
2. 0
3. +1

Reasoning:
𝑐𝑜𝑣(𝑥;𝑦) 𝑛∑𝑥𝑦−(∑𝑥)(∑𝑦)
r= =
√𝑣𝑎𝑟 (𝑥)𝑣𝑎𝑟(𝑦) √[𝑛∑𝑥 2 −(∑𝑥)2 ][𝑛∑𝑦 2 −(∑𝑦)2 ]
6(131)−(6)(−1)
=
√[6(6)−(6)2 ][6(443)−(−1)2 ]
786−1
=
√[36−36][2658−1]
785
=
√0]
=0
(Note that where there is a zero in either the X or Y column, the answer will always be zero, as
multiplication or division by 0 = always 0)
A researcher believes that stress level interferes with people's ability to remember. She gives a list of
items to be memorized to a sample of research participants. While they memorize the items, various
disturbances which cause distraction (for example noise, telephone calls, people entering the room
and talking loudly) are deliberately introduced. After they were given a set amount of time to
memorize the list, each participant's stress level is measured (on a scale where a larger number
implies a higher level of stress), and a note is made of the number of items they remember correctly.
Question 65
The researcher draws a graph of the relationship between level of stress and number of items
remembered. If her expectations are correct, which of the following graphs is she likely to find?

1. Graph A
2. Graph B
3. Graph C

Reasoning:
smaller.
The question therefore relates to an expected negative correlation.
Question 66
The researcher calculates the Pearson product moment correlation coefficient of the relationship
between stress level and number of items remembered. Which of following expressions would best
represent the relationship between level of stress and memory if the researcher's suspicion about
the relationship is true?
1. r > 0
2. r ≠ 0
3. r < 0

Reasoning:
See answer above.
Question 67
Which of the following does not represent a valid value for a chi-square (‫א‬²) test statistic?

1. 0.00
2. 10.00
3. -1.00

Reasoning:
The value of the ‫א‬² test statistic can never be less than zero.
Another interesting fact on ‫א‬² is that the test can only be non-directional (you can hypothesize
that a difference exists, but cannot say anything about the direction of the difference).
Question 68
If there is no relationship at all between two variables, what would be the most likely value of
Pearson's correlation coefficient r, out of the following?
1. -1.0
2. 0.0
3. 0.5
Question 69
The chi-square (‫א‬²) test statistic is used to compare - - - --
1. the frequency distribution of observed data with the frequency distribution of the data as
expected if the null hypothesis is true
2. the variance of observed data with the variance of the data as expected if the null
hypothesis is true
3. the extent to which two variables X and Y varies together in relation to the variance of each
of them

Reasoning:
‫א‬² is used to determine whether two variables are distributed in the same way.
It is a calculation of the difference between the observed and expected frequencies.
It asks, “Does a difference exist between an observed number of responses and an expected
number of responses, based on H0?”
Question 70
What is the expected value for the bottom left cell (i.e. rural males) in the following contingency
table, to be used in computing the chi-square (‫א‬²) test statistic?
Row
Male Female Total
Urban 3 9 12
Rural 3 3 6
Column
Total 6 12 18

1. 3
2. 2
3. 6

Reasoning:
Multiply the column total for Male with the row total for Rural, and divide by the overall total:
E = (6 x 6)/18
=2
October November 2016

Question 1
To refer to a variable as a "manifest' variable implies that it is - - -.
1. hidden
2. observable
3. hypothetical

Reasoning:
A variable is manifest (it is visible in the sense that we can observe it) or latent (it is invisible in the
sense that we need some way to make it appear).
Question 2
The (a) - - - - - variable can be said to influence the (b) - - - - - variable
1. (a) dependent (b) independent

2. (a) operational (b) measured
3. (a) independent (b) dependent

Reasoning:
The dependent variable is dependent on the independent variable, or conversely, the
independent variable influences the dependent variable.
X affects Y (X is the independent variable and Y is the dependent variable)
Question 3
A - - - - - is a guess about certain relationships which may exist among constructs, while a(n) - - - - - is
an explanation of why those relationships exist
1. theory, hypothesis,
2. hypothesis, operationalization
3. hypothesis, theory

Reasoning:
A hypothesis is an educated guess, while a theory is a postulated relation between a set of
constructs.

Question 4
An operational definition defines a - - - - - in terms of - - - - -
1. manifest variable, observable behaviour

2. theoretical construct, observable consequences
3. observable construct, other constructs

Reasoning:
Operational definitions are used to cross the gap between theory and empirical research. It does
this by describing theoretical constructs in terms of observable instances, which can be measured
and used to test a theory.
Question 5
A researcher would make - - - - - based on a - - - - - of data so that she can make - - - - - about the
relationships among variables in the - - - - - which she is studying
1. observations, sample, inferences, population

2. inferences, sample, observations, population,
3. observations, population, inferences, sample
Question 6
Psychological measurements are always imperfect. The way in which a measurement varies around
its 'true' value is referred to as ---.
1. measurement error
2. variance
3. the standard deviation

Reasoning:
One of the consequences of using samples to represent populations is that this always leads to a
certain degree of measurement error, no matter how rigorous our sampling procedure is. Another
source of measurement error lies in the fact that our measurements are imprecise, that the
measurement of a psychological construct is only more or less accurate. This measurement error
is a kind of hidden variable, which we always presume to exist in social scientific research.
Question 7
--- are operationalized to make it possible to - - - them, and the resultant quantities are referred to
as ---.
1. Hypotheses, observe, measurements,

2. Variables, measure, statistics
3. Constructs, measure, variables


Reasoning:
Operationalizing a construct refers to that fact that we have to devise a systematic procedure or
operation to make the construct visible, in such a way that we can measure it. A construct that
has been measured in some way produces a variable.
Question 8
Which of the following represents the main purpose of psychological research?
1. Making predictions of human behaviour

2. Building theories empirically based on observations
3. Gathering data about human behavior

Reasoning:
Psychologists try to develop explanations for human experiences and behavior.
Question 9
Which of the following can be said to be 'constructs' in psychology?
1. Anxiety
2. Hypothesis
3. Theory
Question 10
A hypothesis can be best described as a(n) - - -
1. insight regarding the relationship among variables based on a theory

2. type of statement made by researchers when they are motivating their research
3. prediction of some sort regarding the possible outcomes of a study
Question 11
The process of selecting a subset of a population for a survey is known as - - - - -
1. operationalisation
2. inference
3. sampling
Question 12
The variable manipulated by the researcher in an experiment is called the - - - - -

1. manifest variable
2. independent variable
3. dependent variable

Reasoning:
The independent variable is something that the researcher manipulates, to see how this affects
the dependent variable (in other words, the dependent variable is dependent on the independent
variable).
Question 13
What would you calculate using this equation?
𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝐸𝑣𝑒𝑛𝑡𝑠
P(E) =
𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑃𝑜𝑠𝑠𝑖𝑏𝑙𝑒 𝑂𝑢𝑡𝑐𝑜𝑚𝑒𝑠
1. A z-score
2. The variance
3. A probability
Question 14
If you select one marble randomly from a bag containing 18 red, 17 blue, and 12 green marbles,
what is the probability of the marble being green?
1. 0.26
2. 0.38
3. 0.36

Reasoning:
p(G) = 12/47 = 0.255
Mary, a female second year Bachelor of Arts student, joins an introductory psychology class. She
finds that the class has 9 first year males, 15 first year females, 8 second year males and 12 second
year females (including herself)
Question 15
If one student is randomly selected from this class, what is the probability that it will be Mary?
1. 1/17
2. 1/44
3. 1/20

Question 16
If one student is randomly selected from this class, what is the probability that it will be a second-
year student?
1. 1/20
2. 1/44
3. 20/44
Question 17
If one student is randomly selected from this class, what is the probability that it will be either Mary
OR a male student?
1. 2/44
2. 1/44+17/44
3. 1/27 + 1/17
Question 18
What is p(z < -2.4)?
1. 0.9918
2. 0.4918
3. 0.0082

Reasoning:
Look up in the Table - Probabilities associated with the standard normal distribution (z) in the
appendix.
Question 19
A sample of n=100 exam scores representing exam results of psychology students has a mean of 60
with a standard deviation of 10. John has a mark of 80. Which of the following is John's score if this
was transformed into a z-score?
1. 2
2. 1
3. 4.04

Reasoning:
80−60
z=
10

20
=
10
=2
Question 20
Based on data from a random sample of employees in a specific city, a researcher finds that the
employees spend on average 23 minutes each day commuting to work, with a standard deviation of
8 minutes. Assuming that commuting time is normally distributed, what is the probability that a
randomly chosen employee in this city will spend more than 35 minutes commuting to work each
day?
1. 0.1587
2. 0.0668
3. 0.9332

Reasoning:
35−23
Z=
8
= 1.5.
Looking the value 1.5 up in the probabilities associated with standard normal distribution, under
the “greater than” column (since the question states ‘more than’), the answer is 0.9332.
Question 21
A z-score provides one with the - - - - -
1. measure of how much the scores vary around the mean

2. sum of scores divided by the number of scores in a sample
3. number of standard deviations that a score lies above or below the mean

Reasoning:
The size of the z-score always reflects the number of standard deviations that a particular score
lies above or below the mean.
Question 22
The standard error associated with a specific sample drawn from a population can be estimated
from the sample standard deviation in terms of the - - - - -
1. sample size
2. population size
3. population mean

Reasoning:

Where σ denotes the standard deviation, and n denotes the sample size.
Question 23
A probability of an event occurring depending on something else occurring, such as passing a test
when you do not understand your course, can be described as - - - - -
1. a conditional probability
2. an independent event
3. mutually exclusive events

Reasoning:
CONDITIONAL PROBABILITY - a particular probability is conditional on something else happening.
Event A conditional on Event B happening = P (A B)
Question 24
If 5000 students wrote an exam, 3000 passed with 50% or more and 250 obtained exactly 50%, what
is the value of p(50% pass) for randomly selected students?
1. 0.06
2. 0.083
3. 0.05
Answer: The correct option is

Reasoning:
The formula p (50% pass) should be read as the conditional probability of someone obtaining 50%.
It is clear from the example that any student selected from the given population who obtained
50% or more, has necessarily also passed.
Question 25
Why is the central limit theorem of importance in inferential statistics?
1. Because it informs us how sampling error will increase as the population increases
2. Because it tells us that sampling error will begin to approximate a normal distribution as
samples grow larger
3. Because it shows that the sampling distribution of the means of repeated samples will
approach a normal distribution as sample size increases

Reasoning:
It often happens that we doubt the assumption that the population distribution is normal.
However, the central limit theorem states that, for a large sample size, the sampling distribution
of a mean is close to normal, irrespective of the shape of the population distribution of the

original data. This enables us to make inferences about means and develop test statistics for
means.
Question 26
A very bright student is described as having an IQ that is three standard deviations above the
population mean. If this student's IQ is transformed to a z-score, this z-score would be equal to - - - -
1. µ + 3
2. µ + 3σ
3. 3
Question 27
If a research result looks psychologically important but is found to be not statistically significant,
what might the researcher consider doing when repeating the research?
1. Use a larger sample

2. Set a lower level of significance
3. Use a more powerful statistical test

Reasoning:
Question 28
The nature of the research process and of statistical analysis is such that statistically significant
results are-----
1. also always psychologically important

2. psychologically important if a high level of significance was used
3. not necessarily psychologically important
Question 29
The lower we set the level of significance, the greater the probability of - - - - -
1. rejecting the null hypothesis

2. a type I error
3. a type II error

Reasoning:

We know that the type I error that a researcher is willing to make is controlled by the researcher
by setting the level of significance (α) in advance. The probability of a type II error (β) is not
controlled in advance by the researcher except for the fact that we know that the lower (smaller)
the probability of a type I error (α) the greater (larger) the probability of a type II error (β).
Question 30
A null hypothesis - - - - -
1. states that a treatment or intervention has no effect

2. is indicated by the symbol H1
3. is formulated in terms of sample statistics

Reasoning:
The null hypothesis - the hypothesis of no effect - will state that no relationship exists:
H0: ρ =0
Question 31
When a z-score is used to test a hypothesis, the calculated value is referred to as a - - - - -
1. level of significance
2. parameter
3. test statistic

Reasoning:
Parameters and their corresponding statistics, such as the mean and standard deviation, are thus
appropriate summary values of the distributions involved.
Question 32
A lecturer in educational psychology suspects that the average IQ of her students will be higher than
the population average of µ = 100. To tests this, the hypothesis she has to set up will have to be - - - -
1. directional
2. non-directional
3. dependent on IQs calculated from a sample of data

Reasoning:

A researcher hypothesizes that babies born prematurely will be somewhat less intelligent as young
adults than their peers. She uses the records of various maternity hospitals to identify a random
sample of 25 persons who are now young adults, but who were born more than four weeks
prematurely. She measures the IQ of each, using the SAWAIS. She knows that IQ scores on this test
are distributed normally in the general population, with a mean of 100 and a standard deviation of
15. Suppose she finds that the mean IQ score of her sample is 97.9 and the standard deviation of the
scores is 17.0. She decides to set the significance level to α = 0.05
Question 33
Which of the following best describes the theoretical hypothesis to be tested?
1. Intelligence is determined by date of birth

2. Premature birth is associated with low intelligence
3. Premature birth is not associated with lower intelligence

Reasoning:
Alternative 3 is the null hypothesis.
Question 34
How many of the two constructs mentioned in the theoretical hypothesis have been operationally
defined?
1. none
2. one
3. both
Question 35
Which is the appropriate test statistic to calculate?
1. The t-statistic for the difference between the means of two independent groups
2. The t-statistic for the mean of a single group

3. The z-statistic for the mean of a single group

Reasoning:
This is a single group design, therefore option 1 is eliminated.
Zc test is not designed for dependent measures, only independent.
When the standard deviation is unknown, we use a t-statistic.
Question 36
What are the requirements with regard to the type of statistical test that may be required to
interpret the research results?
1. No statistical test is required

2. A one-tailed statistical test should be performed
3. A two-tailed statistical test should be performed

Reasoning:
One-tailed = directional.
Two-tailed = non-directional.
Since the hypothesis is H1: µ < 100, this requires a directional and therefore one-tailed test.
Question 37
What will be the outcome of the analysis of the results?
1. The null hypothesis will be rejected in favour of the alternative hypothesis

2. The alternative hypothesis will be rejected in favour of the null hypothesis
3. The null hypothesis will not be rejected
Question 38
When a statistical test yields a very small p-value, which of the following statements is most likely to
be correct?
1. The alternative hypothesis is probably false

2. The null hypothesis is probably true
3. The null hypothesis is probably false

Reasoning:
Note first of all that the p-value is concerned with how probable the sample result is given that
the null hypothesis is true. Now, if the p-value is small, we begin to suspect that the null
hypothesis may be false and should be rejected. If the p-value is large on the other hand, the null
hypothesis is probably true.

Question 39
A psychologically unimportant result may turn out to be statistically significant if the researcher - - - -
1. sets a low level of significance

2. uses a large sample
3. reduces the probability of a Type I error

Reasoning:
Question 40
Suppose a researcher has formulated a research hypothesis and has collected the data which must
now be analysed.
1. The researcher must specify a level of significance when formulating the hypothesis and
before analysing the data
2. The researcher must specify a level of significance after analysing the data
3. The level of significance is fixed by convention and the researcher has no choice about this

Reasoning:
The researcher may choose any level of significance in advance and need not be led by
conventional rules. Therefore alternative 3 is incorrect.
The level of significance is a kind of “benchmark” p-value against which the researcher will
compare the actual p-value of his test statistic.
The researcher compares the p-value with a level of significance (α) that he/she chose before
he/she did the sampling and made the observation. This is chosen by the researcher, based on the
risk of being wrong when rejecting the null hypothesis that he or she is willing to take.
Question 41
A researcher finds that the mean calculated from a sample of n = 1000 research participants is ẋ =
52, with a standard deviation of s = 5.8. A subsequent one-sample t-test shows this differs
significantly from the population mean which is known to be µ= 50. The researcher is concerned that
this significant result is a consequence of the large sample size, but should not be regarded as very
important in practical terms. What should the researcher do to check this suspicion?
1. Determine the power of test

2. Calculate the effect size
3. Calculate the standard error

Reasoning:

Question 42
As the sample size increases, the sample becomes a better representation of the population while
the standard error - - - - -
1. decreases
2. remains the same
3. increases

Reasoning:
With each increase in sample size there is a corresponding decrease in the standard error.
Question 43
Cohen's d refers to the - - - - -
1. difference score when two means from dependent samples are compared
2. effect size
3. power of a test

Reasoning:
𝑚𝑒𝑎𝑛 𝑑𝑖𝑓𝑓𝑒𝑟𝑒𝑛𝑐𝑒
Cohen’s d = Effect size = d =
𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝑑𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛
Question 44
A type II error is always made when - - - - -
1. The null hypothesis is not rejected when it is false

2. The alternative hypothesis is rejected when it is false
3. The null hypothesis is rejected when it is true

Reasoning:
Question 45
A researcher draws a single random sample from a population to test his hypothesis about the mean
population score on a psychological test. Scores on this test are distributed normally in the general
population with a known mean but an unknown standard deviation. Which test statistic is the most
appropriate to test his hypothesis?
1. The t-statistic for the mean of a single sample

2. The z-statistic for the mean of a single sample
3. The standard deviation of the sampling distribution of the mean of a single sample

Reasoning:
As a single sample mean is involved but the population standard deviation is unknown, the
appropriate test statistic is a t-statistic for a single sample mean.
Question 46
The probability under the null hypothesis of obtaining a t-value of 2.5 or higher in the case of a one-
tailed test is - - - - - that for a two-tailed test
1. the same as
2. twice
3. half

Reasoning:
A two-tailed p-value (used in the case of a non-directional hypothesis) is twice the size of a one
tailed p-value (see page 66 of the study guide); or, conversely, a one- tailed p-value (used in the
case of a directional hypothesis) is half the size of a two-tailed probability.
The relationship between one-tailed and two-tailed p-values can be summarized as follows:
• One-tailed p-value = (two-tailed p-value) / 2
• Two-tailed p-value = (one-tailed p-value) x 2
However, the question asks not about the relationship between the p-value in a one-tailed vs.
two-tailed test, but about the probability of obtaining a t-value of 2.5 or higher. Therefore,
options 2 and 3 is eliminated and option 1 is correct.
Question 47
Consider the following statistical hypothesis.
H0 µ = 120
H1 µ > 120
If a sample of n=64 is drawn from the relevant population and it is found that ẋ =124.2 and s = 25,
what would be the value of the standard error (sẋ)?
1. 25
25
2.
√64
25
3.
64

Reasoning:
The standard error is the standard deviation of the sampling distribution of the mean.
𝜎
Formula for calculating standard error = σ ẋ =
√𝑛
25
=
√64

Question 48
Suppose you find that the value of a t-test statistic calculated for your research results is 3.0 and the
appropriate p-value 0.02. Assume that the level of significance was set at 0.05. Which conclusion is
appropriate?
1. Reject the null hypothesis

2. Do not reject the null hypothesis
3. Reject the alternative hypothesis

Reasoning:
This p-value is smaller than the level of significance of α = 0.05, and it implies that the null
hypothesis can be rejected in favour of the alternative hypothesis.
Question 49
Suppose the alternative hypothesis states that the population mean is larger than 60. The researcher
should test H0 against H1 if - - - - -
1. the sample mean is larger than 60

2. the sample mean is larger or smaller than 60
3. the p-value is smaller than the level of significance

Reasoning:
If the p-value is smaller than the level of significance (option 3), the null hypothesis should be
rejected (not tested against H1)
Question 50
Susan stated the following hypothesis:
H0 µ = 100
H1 µ > 100
She drew a random sample of 50 persons. Given that the null hypothesis is false, what can Susan
expect the mean of the sample to be?
1. Less than 100

2. Some value different from 100
3. More than 100
A researcher suspects there is a difference between the creative ability of boys and girls in a school
for gifted children. She uses a test for creativity that has been standardised in such a way that the
mean creative ability score for the general population is 50.

Question 51
Which of the following is a plausible way to state the null hypothesis?
1. H0 µB = µG
2. H0 µ = 50
3. H0 ẋB = ẋG

Reasoning:
µ refers to the population mean. However, the researcher is interested in the creative ability of
the boys vs. the girls in the specific school.
Question 52
Which of the following would be an appropriate way of stating the alternative hypothesis?
1. H1 µ > 50
2. H1 ẋB ≠ ẋG
3. H0 µB ≠ µG

Reasoning:
The alternative hypothesis is always H1, (H0 refers to the null hypothesis), therefore alternative 3
is incorrect.
Question 53
A researcher plans to use the t-test to compare two independent samples. What minimum
assumption needs to be met before she may proceed, especially when the samples are relatively
small?
a) the sample variances (or standard deviations) have to be equal

b) the data from both samples has to come from populations that are normally distributed
1. Only (a)
2. Only (b)
3. Both (a) and (b)

Reasoning:
To develop a test for difference between two means (µ1 - µ2) we need to know something about
the statistical distribution. Statisticians have determined that the distribution of the difference
between two normally distributed variables also produces a normally distributed variable.
Furthermore, they have found that as long as the two standard deviations (of the two groups
being compared) do not differ significantly, we can estimate the standard deviation of the pooled
means.
Question 54
Which of the following sample characteristics is most likely to produce a significant result when a t-
test for independent measures is used?

1. A small difference between the means and small sample variances

2. A large difference between the means and small sample variances
3. A small difference between the means and large sample variances

Reasoning:
Remember that the t-value is sensitive to sample size (for a larger sample a smaller effect would
be significant).
Question 55
For an experiment comparing two treatment conditions, an independent measures design would
require - - - - - score(s) for each subject and a repeated measures design would require - - - - -
score(s) for each subject
1. one, one
2. one, two
3. two, one

Reasoning:
A repeated measures design is where the same research participant is observed under more than
one treatment or experimental condition.
Question 56
Consider a situation where two means are being compared with a t-test. If the null hypothesis
happens to be true, one would expect the t-value to have a value close to - - - - -
1. 0
2. 1
3. 1.96

Reasoning:
The bigger the t-value the greater the likelihood of rejecting H0 (as is the case with z-statistics),
because it refers to how far the observed value of the sample statistic differs from the population
parameter that was provided and refers to the areas on the edges of the distribution. Therefore, if
the null hypothesis happens to be true, one would expect the t-value to be close to 0.
Question 57
The alternative hypothesis in the case of a t-test for independent samples would state that - - - - -
1. the two populations being compared have a mean difference of zero

2. there is no mean difference between the two samples being compared
3. the mean difference between the two populations being compared is not equal to zero

Reasoning:
Note that option 1 and option 2 refers to the same principle, but is just worded differently.

Question 58
In which of the following research situations is it most likely that a test for comparing independent
groups will be used?
1. Evaluate the effectiveness of a new medicine used for pain relief by measuring how much
the pain is reduced after taking the medication
2. Evaluate the difference in self-esteem between persons who actively participate in sport and
those who do not participate in sport
3. Evaluate the development of verbal skills between the ages of 2 and 3 years for a sample of
girls

Reasoning:
Option 1 refers to a dependent group, as the same sample will be used before the medication and
then again after the medication.
Option 2 refers to independent groups, one that actively participate in sport and one who does
not.
Question 59
For which of the following research projects would a test for dependent samples not be
appropriate?
1. Comparing the verbal skills of boys with those of girls for three-year old children
2. Comparing pain tolerance before and after taking a new pain medication
3. Assigning participants to one of two groups, so that each participant in one group has the
same IQ as a participant in the other group, when evaluating a workshop for improving
problem-solving skills

Reasoning:
Note that the question refers to when a test for independent samples should be used (conversely
– a test for dependent samples should not be used).
Option 2 refers to dependent samples, and is therefore eliminated.
Option 3 refers to a matched-pairs design – which is an example of dependent groups, and is
therefore eliminated.
Question 60
If a null hypothesis is true, which of the following is the closest to the average value of the tc statistic
for comparing two means that you would expect to find?
1. 0
2. 1
3. 1.96

Reasoning:

The bigger the t-value the greater the likelihood of rejecting H0 (as is the case with z-statistics),
because it refers to how far the observed value of the sample statistic differs from the population
parameter that was provided and refers to the areas on the edges of the distribution. Therefore, if
the null hypothesis happens to be true, one would expect the t-value to be close to 0.
Question 61
Vusi wants to know if students did significantly better on a test the second time they took it. Which
test of statistical significance should he use?
1. The test based on Pearson's r

2. An independent sample t-test
3. A dependent sample t-test

Reasoning:
This is a repeated measures design, where the same research participants are observed under
more than one treatment or experimental condition. This is an example of a dependent sample.
Question 62
A scatter plot is a graphical representation of the relation between - - - - -
1. two variables measured on a nominal scale within a single group

2. two variables measured on a ratio or interval scale within a single group
3. two groups of subjects with regard to a single variable measured on an interval or ratio scale

Reasoning:
better to represent variables on a nominal or ordinal level. Therefore option 1 is incorrect.
A scatter plot is a graph that represents the measurements of two variables on two perpendicular
axes, usually called the x-axis (horizontal axis or abscissa) and the y-axis (vertical axis or ordinate).
Therefore option 3 is incorrect.
Question 63
Which of the graphs below is most likely to represent a Pearson correlation of r = +0 85 between
variables X and Y if the measurements are plotted on a scatter plot?

1. Graph A
2. Graph B
3. Graph C

Reasoning:
smaller.
The question relates to a positive correlation.
Question 64
What is the correlation coefficient between the following values of X and Y?
X 0 0 0
Y -1 0 1
1. -1
2. 0
3. +1

Reasoning:
r= =
√𝑣𝑎𝑟 (𝑥)𝑣𝑎𝑟(𝑦) √[𝑛∑𝑥 2 −(∑𝑥)2 ][𝑛∑𝑦 2 −(∑𝑦)2 ]
As there are a zero in the Y-values, and all the x-values are zero, the calculation of this formula
will result in an answer of zero, since any number multiplied by zero is zero.
Question 65
Which of the following can never have a value of -0.5?
1. The chi-square statistic

2. The z-statistic
3. The Pearson correlation coefficient

Reasoning:
The value of the ²‫ א‬test statistic can never be less than zero.
Another interesting fact on ²‫ א‬is that the test can only be non-directional (you can hypothesize
that a difference exists, but cannot say anything about the direction of the difference).
Question 66
A negative correlation between variables X and Y implies that persons scoring low on X will generally
score - - - - - on Y
1. low
2. either low or high
3. high

Reasoning:
smaller.
Question 67
Which of the following is suitable for representing the ages versus the heights of a group of
children?
1. A scatter plot
2. A contingency table
3. A histogram

Reasoning:
We refer to an interval/ratio level measurement as a quantity or a measurement, and to a
nominal level measurement as a category or categorical variable.
Age and height are both on interval/ratio level.
Question 68
Pearson's r represents - - - - -
1. a comparison between the observed frequencies and the expected frequencies if the null
hypothesis is true, for the distribution of data across two variables
2. the relationship between two variables, when the way in which they vary together is
compared to their individual variances
3. the difference score between two variables relative to their pooled standard deviation

Reasoning:
Option 1 refers to a chi square (‫א‬²) test statistic.

Option 3 refers to Cohen’s d, where estimated mean difference (difference between two
variables) are divided by the pooled standard deviation.
Question 69
A contingency table indicates - - - - -
1. the distribution of the frequencies for a variable

2. the cross classification of two nominal-scale variables
3. the plot of the relationship between two variables

Reasoning:
A contingency table is a table indicating the number of individual objects falling in each cell of
cross-tabulated data. In other words, it is a two-dimensional table in which each observation is
classified in terms of two categories simultaneously. This table represents the observed data, and
is in effect a count (referred to as frequencies or frequency counts) of the number of events falling
within each category.
Option 1 refers to a histogram.
Option 3 refers to a scatter plot.
Question 70
Which of the following is the appropriate formula for the chi square test?
(𝑂𝑡−𝐸𝑡)²
1. ∑
𝐸𝑡
(ẋ−µ‫)א‬
2.
𝑠‫א‬
𝑐𝑜𝑤(𝑥.𝑦)
3.
√𝑣𝑎𝑟 (𝑥) 𝑣𝑎𝑟 (𝑦)

Reasoning:
Option 2 refers to a test statistic - tẋ
Option 3 refers to Pearson’s r
May June 2017

Question 1
The term 'inference' in psychological research refers to - - - - -
1. the process of setting up a hypothesis as a relationship among variables

2. making a prediction or generalization based on existing information
3. the procedures for making a construct visible so that a measurement can be made

Reasoning:

An inference is not the hypothesis, it is a conclusion based on information, where you state that
something you have found has more general implications. It is a generalization based on existing
information.
Question 2
In psychological research, a construct may be a(n) - -
1. measurement based on the careful observation of aspects of humans or human behavior

2. observation of an aspect of humans or human behaviour which was operationalized in
someway
3. hypothetical aspect of humans or human behaviour which we wish to investigate

Reasoning:
Operationalizing a construct refers to that fact that we have to devise a systematic procedure or
operation to make the construct visible, in such a way that we can measure it. A construct that
has been measured in some way produces a variable.
Constructs are:
Question 3
Which of the options below provides the best description of the main purpose of quantitative
research in psychology? Its purpose is to ---
1. develop theories that explain the relationships among observed aspects of human behaviour
and mental processes
2. develop predictions about human behaviour which can be applied with absolute certainty
3. develop hypotheses about relationships that may exist among various constructs

Reasoning:
Inferential statistics are techniques for making generalisations based on imperfect numeric data,
where the conclusions have a high probability of being true, but you can never be completely
certain. Therefore alternative 2 is incorrect.
We want to know not only what the facts are, but also why they appear to be as they are. In other
words, we want to develop theories (and not just hypotheses), which explain why things are as
they appear to be when we observe them. Therefore alternative 3 is incorrect.
Question 4
Operationalising a construct means to - - - - -
1. find an explanation for the construct to explain why it appears as it is

2. make an educated guess on how it relates to other constructs
3. devise a systematic procedure to make a construct observable, so that we can measure it

Reasoning:
This refers to that fact that we have to devise a systematic procedure or operation to make the
construct visible, in such a way that we can measure it.
Option 2 refers to a hypothesis.
Option 1 refers to a theory.
Question 5
Empirical knowledge is knowledge that is based on - - - - -
1. careful reasoning
2. appropriate theories
3. the observation of events

Reasoning:
Knowledge based on observation of physical events is referred to as empirical knowledge (as
distinct from knowledge based on contemplation, unexplained insights, mystical experiences or
claims by authority figures).
Use the following extract from a research proposal to answer Questions 6 to 8
"Generalised anxiety disorder (GAD) refers to a pattern of almost constant worry or tension, even
when there is little or no apparent cause. Both genetic predisposition and stressors in the life of a
particular patient is believed to contribute to this condition. The research will investigate whether the
level of anxiety of persons diagnosed with GAD is actually reduced by psychotherapy. It is expected
that patients receiving therapy will score lower on the Manifest Anxiety Scale than patients not
receiving therapy"
Question 6
"Both genetic predisposition and stressors in the life of a particular patient is believed to contribute
to this condition" is - - - - -
1. the research hypothesis

2. a theory about the causes of GAD
3. a postulated relation between two constructs

Reasoning:
The research hypothesis is that level of anxiety can be reduced by psychotherapy. Therefore
option 1 is incorrect.
“It is expected that patients receiving therapy will score lower…” is a postulated relation.
Question 7
"Whether the level of anxiety of persons diagnosed with GAD is actually reduced by psychotherapy"
describes - - - - -
1. a theoretical prediction about the effect of psychotherapy

2. the operationalization of the construct 'anxiety'

3. the hypothesis to be investigated

Reasoning:
Operationalization of a construct (option 2) refers to that fact that we have to devise a systematic
procedure or operation to make the construct visible, in such a way that we can measure it.
Option 1 is incorrect, as this is not the theory – but a hypothesis. A theory is a postulated relation
between a set of variables.
Question 8
The dependent variable in this scenario is - - - - - and the independent variable is - - - - -
1. whether or not psychotherapy is received, the level of anxiety experienced by patients

1. the effectiveness of psychotherapy, the level of anxiety
2. the level of anxiety experienced by patients; whether or not psychotherapy is received

Reasoning:
The dependent variable is the one that is predicted or explained. Remember, the independent
variable (x) affects the dependent variable(y); {x  y}
Question 9
Mean, range, variance and standard deviation are examples of - - - --
1. inferential statistics
2. test statistics
3. descriptive statistics

Reasoning:
Descriptive statistics are values used to describe the data.
Question 10
A researcher would use a - - - - - to make a(n) - - - - - about the nature of the - - - - -
1. sample, inference; population

2. variable; prediction; construct

3. population, inference, sample

Reasoning:
The entire collection of cases that you are interested in when you make your measurements for a
particular construct is referred to as the population. Because populations can be very large, and
we rarely have access to them, we would draw a sample of observations from the population and
use that sample to infer certain things about the population's characteristics.
Question 11
A measurement that summarizes an aspect of a population is called a - - - - - while a measurement

that describes the same aspect of a sample is called - - - - -
1. construct; variable
2. parameter; statistic
3. statistic, parameter

Reasoning:
Take note of the following important distinctions between samples and populations. Summary
values for populations are called `parameters' and are usually denoted by Greek letters, while
summary values for samples are called `statistics' and are denoted by Roman letters. The
following table contains some familiar summary values and the symbols that are used for them.
Question 12
A - - - - - is a speculative statement about the relationship among - - - - -, based on observations or

expectations
1. hypothesis, statistics
2. theory; variables
3. hypothesis, constructs

Reasoning:
A hypothesis can be informally described as an educated guess. Research usually tries to establish
relationships among constructs in order to develop a theory or to test an existing theory. Usually,
the theory makes it possible for us to make some kind of prediction of how constructs should be
interrelated. We formulate this relationship as a hypothesis, and we test the hypothesis (using

statistical methods) to see if the prediction is true. If it is not true, there is something wrong with
the theory, and we need to reconsider it.
Question 13
A jar contains 5 red, 8 blue, 3 green and 4 yellow marbles. What is the probability that a blindfolded
person would choose a green marble purely by chance?
1. 0.15
2. 0.33
3. 0.50

Reasoning:
𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑓𝑎𝑣𝑜𝑟𝑎𝑏𝑙𝑒 𝑒𝑣𝑒𝑛𝑡𝑠
p(Green) =
𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑝𝑜𝑠𝑠𝑖𝑏𝑙𝑒 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠
4
=
20
= 0.15
Question 14
A class of 10 boys and 11 girls, including Mary and her friend Elizabeth, chooses a class
representative by writing their names on slips of paper, putting these into a box and asking their
teacher to draw one name blindly. What is the probability that either Mary or Elizabeth will be
selected?
1. 1/11
2. 2/11
3. 2/21

Reasoning:
p(Mary OR Elizabeth) = p(Mary) + p(Elizabeth)
= 2/21
Question 15
Which statement best represents an application of the law of large numbers? If I flip a coin 1000
times it will fall heads up - - - - - 500 times
1. approximately
2. exactly
3. at least

Reasoning:
The law of large number states that the number of heads will converge on (i.e. approach) the
theoretical probability of 0,5., and not that it will reach it exactly (alternative 2).

Question 16
The expression "0 05 < P ≤ 0 10" should be interpreted as a probability value - - - - -
1. smaller than 0 05 and larger or equal to 0 10

2. halfway between 0 05 and 0 10
3. larger than 0 05 and smaller or equal to 0 10
Question 17
Suppose that over the years 10 000 students wrote the examinations in PYC 3704-C and that 6000 of
them passed, of which 300 obtained exactly 50%. This means that for randomly selected students
the probability of obtaining exactly 50% is - - - - - while the probability of obtaining 50% or more is - -
1. 0.60, 0.03
2. 0.05, 0.60
3. 0.03, 0.60
Question 18
During the interpretation of psychological measurements the normal distribution is often - - - - -
1. adapted to fit the observed frequency distribution of scores

2. used as a theoretical model for interpreting the observed distribution of scores
3. used to calculate the relative frequency of observed scores

Reasoning:
The normal distribution is a theoretical distribution which is used to determine the probability of a
given score provided the mean and standard deviation are known. It is not dependent on
observed frequencies (alternative 1), nor is it used to calculate the relative frequency of observed
scores (alternative 3) which can only be obtained empirically.
Question 19
The scale along the X-axis of the standard normal distribution indicates - - - - -.
1. probabilities
2. the number of standard deviations below and above the mean
3. the p-values

Reasoning:
The standard normal distribution is a normal distribution divided up into intervals of standard
deviation on the X-axis.

Question 20
The mean and standard deviation of a set of test scores are 20 and 8 respectively. What is the z-
score corresponding to a test score of 14?
1. 1.33
2. 0.75
3. -0.75

Reasoning:
The z-score associated with 14 is (14-20)/8 = -6/8 = -0,75
Question 21
Suppose the height of military recruits is distributed normally with a mean of 1750 mm and a
standard deviation of 50 mm. Drawing repeated samples of 25 recruits each, we expect the standard
deviation of the sample means to be about - - - - - mm.
1. 2
2. 10
3. 50
Question 22
Which of the following formulas give an appropriate way in which the probability of a specific event
E can be calculated?
𝑇ℎ𝑒 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑒𝑣𝑒𝑛𝑡𝑠 𝑡ℎ𝑎𝑡 𝑓𝑎𝑣𝑜𝑢𝑟𝑠 𝑒𝑣𝑒𝑛𝑡 𝐸
1. P(E) =
𝑇ℎ𝑒 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑡ℎ𝑒𝑜𝑟𝑒𝑡𝑖𝑐𝑎𝑙𝑙𝑦 𝑝𝑜𝑠𝑠𝑖𝑏𝑙𝑒 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠
𝑇ℎ𝑒 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑡𝑖𝑚𝑒𝑠 𝑡ℎ𝑎𝑡 𝑒𝑣𝑒𝑛𝑡 𝐸 𝑖𝑠 𝑜𝑏𝑠𝑒𝑟𝑣𝑒𝑑
2. P(E) =
𝑇ℎ𝑒 𝑡𝑜𝑡𝑎𝑙 𝑡𝑖𝑚𝑒𝑠 𝑡ℎ𝑎𝑡 𝑡ℎ𝑒 𝑒𝑥𝑝𝑒𝑟𝑖𝑚𝑒𝑛𝑡 𝑡𝑜 𝑝𝑟𝑜𝑑𝑢𝑐𝑒 𝑡ℎ𝑒 𝑒𝑣𝑒𝑛𝑡 𝑤𝑎𝑠 𝑝𝑒𝑟𝑓𝑜𝑟𝑚𝑒𝑑
1. Definition (a) only
2. Definition (b) only.
3. Both definitions (a) and (b) can be used.
Question 23
What is a principal advantage of transforming measurements to z scores? They enable one to ---
1. determine whether scores are normally distributed around the mean

2. compare a person's scores on tests with different means and standard deviations
3. determine frequency distributions for tests with different means

Reasoning:

Transforming a score from a normal distribution to its associated z-score has an additional
benefit. Transforming a set of measurements, each with a different mean and a different standard
deviation, into a z-score can be used to compare an individual across different distributions.
Question 24
Consider the following Table which represents the mark of a student (X) on each of three subjects
and the class averages for those subjects
Standard
Mean of deviation
Subject Student X class of class
History 50% 40% 5%
Geography 65% 62% 5%
Mathematics 60% 50% 10%
In which subject did Student X do best, relative to his class?
1. History
2. Geography
3. Mathematics

Reasoning:
History z-score = (50-40)/5 = 2
Geography z-score = (65-62)/5 = 0.4
Mathematics z-score = (60-50)/10 = 1
Question 25
Study the histogram below of the exam marks of a group of students in the same class. Note that the
values on the horizontal axis are the class (category) limits
Assume we use this histogram as a basis for making probability predictions. What is the probability
that a student's score will be between 40 and 60?
1. 0.20
2. 0.10
3. 0.30


Reasoning:
30/100 = 0.3
Use the scenario below to answer Questions 26 to 31
A researcher suspects that the addition of certain food supplements to the diet of elderly people will
reduce the decline in cognitive functioning that comes about because of aging. She decides to test
this using a neuropsychological test that measures the speed with which objects are identified (the
Neuropsychological Perceptual Speed or NPS test). The test is standardized in such a way that a
higher score implies a better rate of object recognition. It is known that the distribution of scores on
this test is approximately normal and that a mean of µ=80 and σ=20 was found in the population of
persons older than 65.
To investigate her hypothesis, she obtains a random sample of n=100 persons older than 65. Each
member of this sample is given a daily dose of supplements over a period of six months. At the end
of this time, each person is tested on the NPS test and a mean of ẋ = 86 is found. The researcher
plans to test the hypothesis at α = 0.05.
Question 26
The appropriate research hypothesis suggested by the scenario above is as follows
1. Cognitive functioning declines with age.

2. The cognitive functioning of elderly persons is related to their perceptual speed
3. Rate of object recognition will be better for elderly persons who take the dietary
supplement than for those who do not.
Question 27
The appropriate alternative hypothesis to be tested for this scenario is - - - - -
1. H1: µ > 80
2. H1: ẋ > 80
3. H1 µ ≠ 80
Question 28
The mean of the sampling distribution of the mean is - - - - -.
1. 80
2. 86
3. 20

Question 29
The standard error is - - - - -.
1. 20
2. 2
3. 0.05

Reasoning:
The standard error is given by dividing the population standard deviation by the square root of the
sample size.
𝜎 20
σẋ = = =2
√𝑛 10
Question 30
With the information as given in the scenario, what would be the appropriate statistical test to test
hypothesis?
1. A one sample z-test

2. A two sample t-test
3. A test of the correlation r for a relationship between two variables
Question 31
The appropriate test statistic is calculated and, based on this number, a computer program is used to
determine that the one-sided p-value = 0.022. What conclusion can be drawn?
The null hypothesis - - - - - which implies that the supplement - - - - - cognitive functioning
1. can be rejected, improves

2. can be rejected; does not improve
3. cannot be rejected, does not improve

Reasoning:
The p-value is smaller than α, which is reason to reject H0, and this implies that the supplement
improves cognitive functioning.
Question 32
When applying a statistical test, the probability of a Type I error is equal to - - - - -
1. the p-value of the test statistic under the alternative hypothesis

2. the level of significance
3. the p-value of the test statistic under the null hypothesis

Reasoning:

Level of significance ∝ limits the probability of making a Type 1 error as it sets the maximum
probability.
The p-value represents the probability that the null hypothesis is true: that the effect we see in
our observation is due to chance effects like measurement error. If this probability is small, we
conclude that H0 is not true, and we reject it. This p- value is also a direct indication of the
probability that the null hypothesis is being mistakenly rejected (Type I error).
Question 33
A statistical hypothesis is a formal statement about - - - - -
3. test statistics

Reasoning:
It is important to take note of this: we set up our hypothesis in terms of population parameters,
but we test it through the use of sample statistics.
Question 34
The sampling distribution of a statistic (e.g. of the sample mean) can be calculated if we assume that
the - - - - - hypothesis is true, but not if we assume that the - - - - - hypothesis is true
1. alternative; null
2. null, alternative
3. research, statistical
Question 35
When a statistical test yields a large p-value, which of the following statements is most likely to be
correct?
1. The alternative hypothesis is probably true

2. The null hypothesis is probably false
3. The null hypothesis is probably true.

Reasoning:
Note first of all that the p-value is concerned with how probable the sample result is given that
the null hypothesis is true. Now if the p-value is small, we begin to suspect that the null
hypothesis may be false and should be rejected. If the p-value is large on the other hand, the null
hypothesis is probably true.
Question 36
The hypothesis "H1: µ < 50" is a - - - - - hypothesis and requires a - - - - - statistical test

1. non-directional, two-tailed
2. directional, two-tailed
3. directional, one-tailed

Reasoning:
Question 37
When applying a z-test to compare a sample mean to a known population mean, the p-value
represents the probability of - - - - -
1. rejecting the null hypothesis if it is false

2. obtaining the mean found in the sample of data under the alternative hypothesis
3. obtaining the mean found in the sample of data under the null hypothesis

Reasoning:
The z-test for population means is a hypothesis test that compares a hypothesized mean from the
null hypothesis to a sample mean, when the population standard deviation is known.
Question 38
When applying a statistical test, a decision is reached by comparing the - - - - - to the - - - - -
1. p-value, level of significance

2. p-value, test statistic
3. test statistic, level of significance

Reasoning:

We compare the p-value with a level of significance (α) that we chose before we did the sampling
and made the observation.
Question 39
1. rejecting the null hypothesis

2. Type II error
3. a Type I error

Reasoning:
We know that the type I error that a researcher is willing to make is controlled by the researcher
by setting the level of significance (α) in advance. The probability of a type II error (β) is not
controlled in advance by the researcher except for the fact that we know that the lower (smaller)
the probability of a type I error (α) the greater (larger) the probability of a type II error (β).
Question 40
For a measurement (x) from a population with µ = 80 and σ = 10, calculate the z-score corresponding
to x = 95
1. 0.25
2. 0.75
3. 1.50

Reasoning:
(95-80)/10 = 1.5
Question 41
Given that a population with µ = 80 and σ = 10 follows a normal distribution, determine p(x ≥ 95)
(Hint use the result of the previous question and select the closest option below)
1. 0.0668
2. 0.4332
3. 0.9332

Reasoning:
Look up the “larger portion” value on the z-table for 1.5.
Question 42
When doing statistical testing, the size of the level of significance depends on - - - - -.
1. a choice made by the researcher

2. the calculation of a test statistic
3. the p-value under H0


Reasoning:
conventional rules.
Question 43
What does it mean to say, "the difference between the means of groups A and B is statistically
significant"?
1. It is unlikely that the alternative hypothesis will be true.

2. The sample result is more probable under the alternative hypothesis.
3. The null hypothesis explains the sample result
Question 44
Which symbol is conventionally used to indicate the value of the maximum probability that an error
would be made if the null hypothesis is rejected which a particular researcher is willing to allow?
1. α
2. σ
3. ρ

Reasoning:
The type I error that a researcher is willing to make is controlled by the researcher by setting the
level of significance (α) in advance. α is deliberately chosen as the maximum probability of making
a Type I error that the researcher is willing to risk.
Question 45
The power of a statistical test refers to the - - - - -
1. test's ability to give small p-values if the sample size is large

2. test's ability to detect significant results or the 'accuracy' of the test
3. probability that an error of Type I will not be made when the test is used

Reasoning:
The ability of a statistical test to detect a significant relationship between variables when such a
relationship does in fact exist, is referred to as its power. This is the inverse of a Type II error: it is
the probability of rejecting H0 when, in fact, it is false and H1 is true. To put it succinctly, it is the
probability of correctly rejecting a false null hypothesis.
Question 46
After finding that a significant difference exists between male and female participants on a test
which tests level of creativity, a researcher decides to also calculate an effect size, using Cohen's d.
This is used to determine - - - - -.

1. whether a significant effect is sufficiently great to be meaningful from a practical point of

view
2. the size of the error that would be made if the null hypothesis is rejected
3. the ability of a statistical test to detect a significant relationship between variables

Reasoning:
We have to be careful how we interpret significant results.
A p-value of smaller than our chosen level of significance (a) simply implies that, relative to this
sample, it is improbable that the effect we see in our observations is purely due to chance. It does
not imply that the effect is big or important. This is something that we have to decide by looking
at what the data means, and this is done through Cohen’s d-test.
Question 47
A researcher wants to test the hypothesis that the mean depression score on a depression scale for
patients diagnosed with clinical depression is greater than 120. The statistical hypothesis to be
tested is
H0: µ = 120
H1: µ > 120
She uses a random sample of n=64 drawn from the population of diagnosed patients and finds that ẋ
= 127 and s = 24
Which of the values below is the closest to the correct value of the standard error Sẋ?
1. 0.37
2. 3.0
3. 24

Reasoning:
= 24/8
=3
Question 48
Suppose H0: µ = 100 is tested against H1 µ > 100 with α =0.05. If the t-statistic based on a sample of
data is found to be tẋ = 1.20 and the two-tailed p-value is 0.06, what decision regarding the
statistical hypothesis can be taken?
1. Reject H0 and accept H1.

2. Reject H1 and accept H0
3. Do not reject H0 and accept H1

Reasoning:

Because the alternative hypothesis is directional, (>) we apply a directional test. This requires that
we divide 0.06 by 2, which gives 0.03. As 0.03 is less than 0.05 (the significance level), the null
hypothesis should be rejected and the alternative hypothesis accepted.
Question 49
Suppose the alternative hypothesis states that µ > 60. The researcher should calculate a test statistic
to test H0 against H1 if the - - - - -
1. sample mean is larger than 60

2. sample mean is smaller than 60
3. sample mean differs from 60
Question 50
The following list contains a number of situations where a researcher may consider using a variation
of the t-test.
a. To compare two group means

b. To determine whether a relationship exists between two continuous quantitative
variables
c. To compare a group mean with a constant value
Two of the statements above are true. Choose the correct set of true statements from the list below
1. (a) and (b)

2. (a) and (c)
3. (b) and (c)

Reasoning:
The notion of the relationship between two continuous variables (option b) and how the size of
the relationship can be expressed in terms of a correlation between them (the index of
association is the Pearson product-moment correlation coefficient). This coefficient can also be
used as a test statistic. Therefore, option b is eliminated.
The t-test is the most commonly used method to evaluate the differences in means between two
groups.
Question 51
An educational psychologist wants to establish if raised expectations has an effect on how students
do in a mathematics test. She selects 100 students at random. Half of the students (the control
group, referred to as Group 1) were told that they have to do 20 mathematics problems, but that
this is just an exercise to practice their skills. The remaining 50 students (the treatment group, Group
2) are told to complete the same problems, but that the marks would count towards their final exam
mark. She decides to use a t-test to compare the results. Which of the test statistics given below is
the appropriate test for her to use?


Reasoning:
Question 52
Samples can be considered independent when - - - - -
1. the sample comes from the assignment of subjects to a treatment or experimental group
and this is varied to see how it affects certain measurements
2. care was taken that the samples are drawn under different experimental conditions
3. the composition of one sample is not systematically related to the composition of the other
one

Reasoning:
Samples are considered as comprising independent groups if the composition of the one sample
in no way affects, in any systematic way, the composition of the other sample.
Base your answers to Questions 53 and 54 on the following scenario:
A researcher wants to investigate the effect of a noisy environment on a task that requires
concentration. The researcher suspects that people exposed to a noisy environment will react
significantly slower in a reaction-speed experiment than those who work in a quiet environment.
Participants from a random sample of 100 people are requested to perform a test where they have to

react to a stimulus on a computer screen by pressing a button as fast as possible. The average
reaction time of each participant in a quiet environment is recorded for 20 trials. After a break for
refreshments, the same participants are asked to repeat the same task a second time. This time
however, there are sounds of people in a nearby room playing music and having a loud conversation.
The participants are unaware that this is a recording. Their reaction times over the same 20 trials are
again recorded. The sample statistics below are the average reaction times (in milliseconds) for each
condition.
Condition 1 – no noise ẋ1 = 13.8, s1 = 4.1
Condition 2 – noisy environment ẋ2 = 14.3, s2 = 3.5
Question 53
Given the scenario above, what type of statistical test is best suited to confirm the relevant
statistical hypothesis?
1. A one-tailed t-test for a single group

2. A two-tailed t-test for independent groups
3. A one-tailed t-test for dependent groups

Reasoning:
This repeated design is a dependent sample group, as the same group was used in both
applications of the test.
Question 54
After doing the appropriate test, the researcher gets a statistically significant result. He notices
however that the difference between the means of the sets of reaction times is quite small. He is
unsure whether this difference is large enough to be of practical importance. Which of the following
strategies would be the most appropriate to get a better idea of the practical usefulness of the
result?
1. Calculating the effect size, using Cohen's d

2. Calculating the correlation coefficient, using Pearson's r
3. Calculating the power of the test, β

Reasoning:
β refers to a Type II error, and not the power of the test. Option 3 is factually incorrect.
Question 55
A researcher wants to test the following hypotheses
H0: µ1 = µ2
H1: µ1 > µ2
On the basis of data provided, the output from a computer program indicates that a t-value of t =
1.72 was found, with the p-value for a two-tailed test given as p = 0.056. What should the researcher
do to evaluate this result at a level of significance of α = 0 05?

1. Divide the p-value by 2 before comparing it with α

2. Multiply the p-value by 2 before comparing it with α
3. Divide α by 2 before comparing p to α

Reasoning:
> refers to directional, and therefore one-tailed test.
A researcher suspects that a relationship exists between colour perception and visual memory (i.e.
the capacity to recall visual information) She suspects that high ability to detect colours rapidly acts
as an aid to the capacity of visual memory. A group of 100 research participants are divided into two
groups, based on the capacity of their visual memory, as determined by an appropriate test. One
group (Group 1) of n1=44 displays high recollection of visual images, the other group (Group 2) of
n2=56 scores low on the test. Each participant from each of the groups are then tested on how many
colours they can recall of objects they see very briefly displayed on a computer screen.
Question 56
Which is the most appropriate research hypothesis for the researcher to test?
1. The mean of the number of colours recalled by the participants with a good visual memory
will differ significantly from the mean number of colours recalled by those with a limited
visual memory
2. The mean of the differences between the number of colours recalled by the participants
with a good visual memory and those with a limited visual memory will be significantly
greater than zero
3. The mean of the number of colours recalled by the participants with a good visual memory
will be significantly greater than the mean number of colours recalled by those with a
limited visual memory
Question 57
Which is an appropriate way to formulate the alternative hypothesis for the analysis of the results?
1. H1: µ1 < µ2
2. H1: µ1 > µ2
3. H1: µ1 ≠ µ2
Question 58
Which is the appropriate test statistic to be calculated when analyzing the results of this research?
1. The t-statistic for the difference between the means of two independent samples
2. The t-statistic for the difference between the means of two dependent samples.

3. The test statistic based on the correlation coefficient r for the relationship between two
variables (visual memory and recall of colours).
To test the efficacy of a workshop aimed at improving people's interpersonal skills, a researcher
applies a scale which rates the interpersonal skills of 30 participants before and after they participate
in the workshop.
Question 59
The interpersonal skill measurements from before the workshop and those after the workshop
should be regarded as samples which comes from - - - - - groups.
1. random
2. independent
3. dependent
Question 60
1. The t-statistic for the mean of a single sample.

2. The t-statistic for the difference between the means of two dependent groups
3. The t-statistic for the difference between the means of two independent groups.
Question 61
When studying correlations in research, one investigates the relation between - - - - -
1. the mean of a single sample of subjects and a population mean

2. two dependent groups of subjects, with respect to a single variable
3. two variables measured on the same group of subjects
Question 62
A scatter plot is a graphical representation of - - - - -
1. the relationship between two variables measured on a nominal scale within a single group
2. the frequency distribution of a sample of measurements
3. the relationship between two variables measured on a ratio or interval scale within a single
group

Reasoning:
Question 63
A positive correlation between variables X and Y implies that if a person scores low on X, their score
on Y will probably be - - - - -
1. high, irrespective of whether the correlation is statistically significant

2. low, irrespective of whether the correlation is statistically significant
3. either high or low, but the relationship will be statistically significant

Reasoning:
A positive correlation implies that as one variable changes, the other changes in the same
direction. A high value on X will imply a high value on Y, while a low value on X will be matched by
a low value on Y.
Question 64
Which of the following can take on a value of -0.5?
1. A probability
2. A level of significance
3. A correlation coefficient

Reasoning:
Probabilities and levels of significance cannot take on a negative value.
Question 65
What is the most likely value of the correlation coefficient between the following values of variables
X and Y?
X 2 7 4 5 1
Y 2 7 4 5 1
1. -1
2. 0
3. +1

Reasoning:
r= =
√𝑣𝑎𝑟 (𝑥)𝑣𝑎𝑟(𝑦) √[𝑛∑𝑥 2 −(∑𝑥)2 ][𝑛∑𝑦 2 −(∑𝑦)2 ]
5(95)−(19)(19)
=
√[5(95)−(19)2 ][5(95)−(19)2 ]

475−361
=
114
=1
(Note than when the X and the Y numbers are exactly the same – the result is always 1)
Question 66
A researcher hypothesizes that a relationship should exist between spatial ability and general
aptitude for mathematics. She collects the results of a sample of n = 100 school children for a
mathematics test and also measures the spatial ability of each child with a test that measures a
person's ability to rotate objects mentally on a 10-point scale.
Which of the following is the most appropriate way to express the null hypothesis for this research?
1. r = 0
2. µ = 0
3. p = 0

Reasoning:
Where we use `r' for the sample coefficient, we shall use the ρ for the population correlation
coefficient.
Note that as usual the hypothesis is formulated in terms of the population correlation coefficient,
as the researcher wants to draw a conclusion about the whole population, and not just about the
representative sample for which data is collected.
Question 67
A number of psychiatric patients are classified into one of four categories as schizophrenic, severely
depressed, bipolar disorder and others. Which of the following is suitable for cross-classifying this
information against the gender of these patients?
1. A contingency table
2. A scatter plot
3. A histogram

Reasoning:
Both variables are categorical (nominal) in nature, with gender being a dichotomy.
As part of an employment equity programme, a researcher is asked to investigate the distribution of

male and female staff members across different types of work in a particular IT company. After
collecting some data, she creates the table below, which represents the observed frequencies of
managers, administrative staff and staff that provides technical services in the company, cross-
classified with genders of the staff members.

Managerial Administrative
Staff Staff Technical Staff
Female 4 6 2
Male 6 4 8
Question 68
Based on the contingency table above, what would the expected frequency of observations in the
cell for female staff who provide technical services be, if no interactions exist between the variables
gender and type of work?
1. 2
2. 4
3. 12

Reasoning:
Multiply the column total for Female with the row total for Technical Staff, and divide by the
overall total:
E = (12x10)/30
=4
Question 69
Given the scenario, which of the following would be the most appropriate statistical test to use to
establish whether a relationship exists between gender and type of work?
1. The t-test for two independent samples

2. The chi-square (‫א‬²) test statistic

Reasoning:
The question is:
Is my dependent variable nominal, ordinal, interval, or ratio?
• If nominal, use chi square
• If ordinal, use chi square
• If interval/ratio, use correlation or t-test
The independent variable is gender and the dependent variable is type of work. Both are nominal
(categorical).
A test of the association between two categorical (nominal scale) variables, where both variables
are considered to be nominal (or categorical). The appropriate test statistic is the ‫א‬² test of
association for contingency tables.
Question 70
Based on the previous question, which of the following is the appropriate formula for the test
statistic which the researcher should use to establish whether a significant relationship between
gender and type of work exists?


Reasoning:
Option 1 refers to the tc test statistic.
Option 2 refers to the Pearson r formula.
Option 3 refers to the Chi square ‫א‬² formula.
October November 2017

Question 1
The process of finding a way to measure a construct so that it can be represented by a variable is
referred to as - - - - -
1. inference
2. operationalization
3. setting a hypothesis

Reasoning:
Operationalization of a construct refers to that fact that we have to devise a systematic procedure
or operation to make the construct visible, in such a way that we can measure it.
Question 2
Mean, range, variance and standard deviation are examples of - - - - -
1. variables
2. descriptive statistics
3. inferential statistics

Reasoning:
Descriptive statistics are values used to describe the data.
Question 3
A theory is a(n) - - - - -
1. process of careful observation

2. method to make a construct observable
3. explanation of why facts are as they are observed to be


Reasoning:
Option 2 refers to operationalization.
Question 4
The process of selecting a subset of a population for a survey is known as - - - - -
1. triangulation
2. sampling
3. operationalization

Reasoning:
Operationalization of a construct (option 3) refers to that fact that we have to devise a systematic
procedure or operation to make the construct visible, in such a way that we can measure it.
Question 5
An inference is - - - - -
1. an explanation of why certain things are as they are observed to be

2. an educated guess about how certain phenomena may be interrelated
3. a generalization from a sample to a population which have a high probability of being true

Reasoning:
something you have found has more general implications. It is a generalization based on existing
information.
Option 1 refers to a theory.
Option 2 refers to a hypothesis.
Question 6
"Empirically" means "based on .... "
1. theory
2. observations
3. facts

Reasoning:
Knowledge based on observation of physical events is referred to as empirical knowledge (as
distinct from knowledge based on contemplation, unexplained insights, mystical experiences or
claims by authority figures). By means of observation or experience rather than theory or pure
logic.
Question 7
Which of the following best describes "latent"?

1. observable
2. hidden
3. independent

Reasoning:
A latent variable cannot be observed directly. Latent variables are hypothetical or hidden.
Question 8
A psychologist has a theory that visual perceptual ability influences the marks that learners will get
in a mathematics test. In this example 'visual perceptual ability' the --- variable
1. dependent
2. independent
3. hidden

Reasoning:
The independent variable (x) affects the dependent variable(y); {x  y}
Question 9
When a construct is measured the resulting quantity is referred to as a ---
1. variable
2. mean
3. standard error

Reasoning:
A construct that has been measured in some way produces a variable.
Question 10
A psychologist is interested in studying the interaction between small groups of four to five people in
each group. He suspects that the interactions between such groups can be described in similar terms
to the interactions between individual persons. In order to be able to do a scientific study of this (a) -
-- question, he would have to provide a(an) (b) --- definition of the (c) --- called "interaction"
1. (a) research (b) operational (c) construct

2. (a) experimental (b) research (c) statistic
3. (a) hypothetical (b) empirical (c) parameter
Question 11
The variable manipulated by the researcher in an experiment is called the - - - - - variable
1. empirical

2. independent
3. dependent

Reasoning:
The independent variable (x) affects the dependent variable(y); {x  y}
The researcher manipulates x to see its effect on y
Question 12
The term 'population' refers to - - - - -.
1. the entire group from which the data is to be selected

2. a subset of cases selected to represent the entire group
3. the entire set of variables which will be considered in the research

Reasoning:
The entire collection of cases that the researcher is interested in when making the measurements
for a particular construct is referred to as the population.
Option 2 refers to a sample.
Option 3 refers to variables – not to cases.
Question 13
The symbol ẋ refers to - - - - -, while µ refers to - - - - -
1. sample mean, population mean

2. sample mean, sample standard deviation
3. population mean, population variance
Question 14
In probability theory, the number of distinct events that could possibly occur during the
performance of an experiment is referred to as the - - - - -
1. probability distribution
2. frequency distribution
3. sample space

Reasoning:
A frequency distribution (option 2) is a table or graph showing how many subjects in a sample
obtained each possible score on a test.
A probability distribution (option 1) is a mathematical function that, stated in simple terms, can be
thought of as providing the probabilities of occurrence of different possible outcomes in an
experiment.)
Sample space (option 3) is a list of all the possible outcomes. All the possible outcomes of a
statistical experiment are called the sample space (which we also call a population) of the
experiment.

Question 15
The table below gives frequency distribution of the exam marks of a number of students in a
psychology exam.
Number of students
in this range
Range of marks (frequency count)
40% and below 8
41%-50% 12
51%-60% 20
61%-70% 30
71%-80% 22
81% and above 18
What is the probability that a student will get a mark of between 51 % and 70%? (Rounded off)
1. 0.45
2. 0.82
3. 0.18

Reasoning:
p(51-60 + 61-70)/110
= 0.45
Question 16
A test for short-term memory capacity is normally distributed with a mean of µ = 100 and a standard
deviation of α = 10. What is the probability that any person, chosen at random, will have a score of x
= 125 or more on this test?
1. 0.0668
2. 0.0228
3. 0.0062

Reasoning:
Calculate the z-score.
(125-100)/10
= 2.5.
Now look up the value in the “smaller portion” in the z-tables.
Question 17
Suppose the weights of the population of military recruits are distributed normally with a mean of
64 kg and a standard deviation of 8 kg. Different samples of these recruits, each with a sample size

of 16, are drawn repeatedly. We would expect the standard deviation of the sample means (the
standard error) to be about - - - - - kg
1. 2
2. 8
3. 4

Reasoning:
𝑠
sẋ =
√𝑛
8
=
4
=2
Question 18
A marble is drawn at random from a box containing 6 red marbles, 4 green marbles and 5 blue
marbles. If one marble is drawn at random from the box, what is the probability that it will be red?
(Rounded off)
1. 0.07
2. 0.4
3. 0.17
Question 19
There are 19 female students and 8 male students in a group of psychology students. Of the 19
females, only 4 has no brothers or sisters, while 3 of the males are only children. If a student is
selected at random from the group, what is the probability that it will be a female with no siblings?
(Results are rounded off).
1. 4/19=0.21
2. 19/27 = 0.70
3. 4/27 = 0.15
Question 20
A variable is normally distributed with a mean of 50 and a standard deviation of 10. If this variable is
transformed to a standardized normal distribution, what would the values of the mean and standard
deviation on the z-distribution be?
1. Mean z = 0, Standard deviation z = 1



Reasoning:
The z-distribution refers to a variable that is normally distributed with a population mean of µ = 0
and a standard deviation of σ = 1 (generally referred to as the standardized normal distribution).
Question 21
The probability of an event can be determined by - - - - -
1. the set of all possible values of a statistic when all possible values of a fixed size are taken
from the population
2. observing the number of times that the event occurs, and dividing this by the number of
events that could possibly occur during the specific experimental situation
3. the distribution of means obtained from all possible samples which can be established by
applying the central limit theorem

Reasoning:
𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑓𝑎𝑣𝑜𝑟𝑎𝑏𝑙𝑒 𝑒𝑣𝑒𝑛𝑡𝑠
p(E) =
𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑝𝑜𝑠𝑠𝑖𝑏𝑙𝑒 𝑂𝑐𝑐𝑢𝑟𝑎𝑛𝑐𝑒 𝑜𝑓 𝑡ℎ𝑒 𝑒𝑣𝑒𝑛𝑡
Question 22
By convention, the total area under the standard normal curve is set equal to - - - - -
1. zero
2. its standard deviation
3. one

Reasoning:
The total area under the curve gives the probability of the interval - ∞ and + ∞, and is equal to +1
(i.e., the probability of any value of z falling between minus and plus infinity is equal to 1).
Question 23
The mean and standard deviation of a set of test scores are 20 and 8 respectively. If the z-score
which corresponds to a test score of 14 is calculated, in which of the intervals listed below would it
fall?
1. 0.5
2. -0.75
3. 0.75

Reasoning:
To calculate the z-score, we use the formula in the study guide. If we insert the values given into
the formula, we obtain (14-20)/8 = - 6/8 = - 0,75.

Question 24
The distribution of sample means for a number of samples drawn from the same population can be
determined because of - - - - -
1. the z-distribution
2. the central limit theorem
3. statistical inference

Reasoning:
There is one form of the normal distribution that is of special importance. This curve has a mean
of µ = 0 and a standard deviation of σ = 1 and is known as the standard normal distribution, and is
by convention indicated with the letter `z' (so it is also referred to as the z-distribution). The
measures on this distribution are referred to as standard scores or z-scores.
If we know how events are distributed, we can determine the probability that the event will
occur. The standard normal distribution makes it possible for us to apply this knowledge to
normal distributions in general.
Option 2, the central limit theorem, refers to the fact that it often happens that we doubt the
assumption that the population distribution is normal. However, the central limit theorem states
that, for a large sample size, the sampling distribution of a mean is close to normal, irrespective of
the shape of the population distribution of the original data. This enables us to make inferences
about means and develop test statistics for means.
Question 25
The asymptotic property of the normal curve refers to the fact that - - - - -
1. the curve is bell-shaped

2. the endpoints of the curve get continuously closer to the X-axis without ever touching it
3. the curve is symmetrical

Reasoning:
Asymptotic means that the two tails never touch the horizontal axis, moving ever closer to
infinity, because there is always some probability that more extreme values will occur.
Question 26
Consider a hypothesis which describes a possible relationship between two variables. The null
hypothesis refers to which specific kind of relationship between the variables?
1. No relationship
2. A positive relationship
3. A significant relationship

Reasoning:
The null hypothesis implies no effect – therefore no relationship between the variables.

Question 27
Statistical hypotheses are statements about - - - - -
3. the z-distribution

Reasoning:
We set up our hypothesis in terms of population parameters, but we test it through the use of
sample statistics.
Question 28
Suppose we have stated H0 µ = 10, and H1 µ < 10, and find that the sample mean corresponds to a z-
score of -3. This means that the corresponding p-value - - - - -
1. need not be found to reach a decision

2. is equal to 0.0026
3. is equal to 0.0013
Answer: The correct option is

Reasoning:
We know that a z-scores of -3 (look in the z-tables) are extremely unlikely. We also know that the
negative sign indicates that H1 has a logical chance of being correct instead of H0 (the result is in
the correct direction). This result of -3 is highly unlikely under H0 and H0 should be rejected in
favour of H1. This all means that we need not find the p-value because we know it will be very
small.
Question 29
The hypothesis "H1 µ > 50" is a (a) - - - - - hypothesis and requires a (b) - - - - - statistical test
1. (a) directional (b) two-tailed

2. (a) non-directional (b) two-tailed
3. (a) directional (b) one-tailed
Question 30
The level of significance of a statistical test - - - - -
1. refers the p-value which is calculated from the test statistic

2. indicates the maximum risk that a researcher is willing to take of making an error of Type I
3. is used to indicate the probability of making an error by not rejecting the null hypothesis

Reasoning:
The p-value is compared with a level of significance (α) that is chosen before the sampling is done
and observations made. This is chosen by the researcher, based on the risk of being wrong when

rejecting the null hypothesis that he or she is willing to take. (Rejecting the null hypothesis when it
is in fact true is called a Type I error.)
Question 31
When applying a statistical test, if the p-value is larger than the level of significance, we - - - - - the
alternative hypothesis
1. do not accept
2. fail to reject
3. accept

Reasoning:
If the p- value associated with the test statistic is smaller than the α-value, the null hypothesis is
rejected and the alternative hypothesis accepted.
If the p-value associated with the test statistic is greater than α-value, the null hypothesis is not
rejected and the research hypothesis therefore not confirmed. Do not accept H1.
Question 32
A type II error occurs when - - - - -
1. the null hypothesis is rejected when it should not be rejected

2. the null hypothesis is not rejected when it should be rejected
3. the alternative hypothesis not accepted when it should be accepted

Reasoning:
Type II error (β) – not rejecting H0 when H0 is actually false and H1 is true.
Option 1 refers to a Type I error.
Base your answers to Questions 33 to 37 on the following scenario:
Rose is interested in the problem of depth perception. She wonders whether fine artists who have
made a study of the problem of perspective would be better at judging depth than people in general.
She decides to investigate this using a test for depth perception which was standardized on the
general population with a mean of 5, where a greater number implies better depth perception on a
scale of 1 to 9. She randomly draws 100 students who had graduated from a school for fine arts and
tests each of them on the depth perception test. She finds that the mean depth perception score of
her sample is 6.2 and the sample standard deviation is 1.7.
Question 33
How would you describe the population investigated in this research?
1. The general population

2. Fine artists who studied perspective
3. Fine artists from a specific school for fine arts

Question 34
Which of the following best describes the research or theoretical hypothesis to be tested?
1. Depth perception is related to artistic ability

2. Visual artists have a superior ability for depth perception than people in general
3. The relationship between depth perception and artistic ability is statistically significant
Question 35
Which of the following are appropriate null and alternative hypotheses?
1. H0: µ = 5, H1 µ ≠ 5
2. H0: µ = 5, H1 µ > 5
3. H0: µ ≠ 5, H1 µ > 5

Reasoning:
(or a group mean and a specific constant value) do not differ. Therefore option 3 is eliminated.
Question 36
Which is the correct value of the standard deviation of the sampling distribution of the mean (the
standard error) of the depth perception scores?
1. 1.7
2. 0.017
3. 0.17

Reasoning:
The spread or dispersion of the sampling distribution of means is given by the standard deviation
of the sampling distribution of means (i.e. the standard error). The formula for determining
this standard deviation is σ/n. Therefore 1,7/100.
Question 37
1. The t-statistic for the mean of a single group

2. The z-statistic for the mean of a single group
3. The t-statistic for the difference between the means of two dependent groups

Reasoning:
• We calculate and use the z-statistic for a single-groups design (zx) to test a hypothesis
when the population standard deviation (σ) is known.

• We calculate and use the t-statistic for a single-groups design (tx) to test a hypothesis
when the population standard deviation (σ) is unknown.
Question 38
When two population means are compared, the p-value is calculated to represent the probability of
observing a specific difference between the sample means given that - - - - -
1. H0 is true
2. H1 is true
3. H0 is false
Question 39
What should a researcher do if a small difference between two means based on a large sample is
found to differ significantly, to determine whether the outcome is of practical importance?
A psychologically unimportant result may turn out to be statistically significant if the researcher
1. set a lower level of significance

2. determine the power of the statistical test
3. calculate the effect size

Reasoning:
Question 40
The mean score of a sample of research participants is compared with a population mean of 20 for
that particular questionnaire. The following hypothesis is to be tested
H0: µ = 20
H1: µ ≠ 20
A researcher draws a random sample of 50 persons and obtains a mean score of 25 and a standard
deviation of 4 on this questionnaire. If the null hypothesis is true, what would you expect the
probable value of the mean of the sample to have been?
1. 20
2. 25
3. Not equal to 20

Question 41
When two means are compared, the p-value expresses the probability that a difference which is
observed between the means in a sample of measurements - - - - -
1. will be significant
2. is due to the alternative hypothesis
3. is due to chance or sampling error

Reasoning:
The p-value always reflects the probability that the result is due to chance.
Question 42
Which symbol is conventionally used to indicate the value of the maximum probability that an error
would be made if the null hypothesis is rejected which a particular researcher is willing to allow?
1. α
2. β
3. σ

Reasoning:
The value of a represents the maximum risk that we are willing to take of making a Type I error by
rejecting H0 in error.
Question 43
Cohen's d refers to the - - - - -
1. difference score when two means from dependent samples are compared
2. effect size
3. power of a test

Reasoning:
Cohen’s d = Effect size
Question 44
Effect size is calculated to determine - - - - -
1. whether an effect is statistically significant or not

2. the ability of a statistical test to detect a significant relationship between variables when
such a relationship does in fact exist
3. whether a significant effect is meaningful from a practical point of view irrespective of
sample size

Question 45
A random sample of n= 100 people are tested to see how many items they can recall from a list with
pictures of 12 items. The distribution of the results is found to be more or less normal with a mean
of ẋ = 7 and a standard deviation of s = 20. What is the probability that a specific person, chosen at
random from the general population, will remember 10 or more items from the list?
1. Less than 0
2. Between 0 and 0.1
3. Greater than 0.1

Reasoning:
𝑥− µ
z=
𝜎
= (10-7)/20
= 0.15
Also note that the question asks “10 or more”, indicating the possibility that the specific person
could score anything above 10, i.e. 12, therefore 0.25, which is also higher than 0.1.
Question 46
Under which condition would a researcher use a t-statistic to test a hypothesis about an unknown
population mean µ?
The value of the (a) - - - - - is (b) - - - - -
1. (a) population standard deviation σ, (b) unknown

2. (a) standard error Sẋ, (b) unknown
3. (a) population standard deviation σ, (b) known
Base your answers to Questions 47 to 49 on the following scenario.
Suppose that the memory span of adults is normally distributed with a mean of µ = 7 items and a
standard deviation of σ = 2 items. A researcher is investigating the impairment of memory among
persons who have been diagnosed as suffering from Korsakoff's syndrome (a neurological disorder
linked to chronic alcohol abuse). He intends to test his prediction on a sample of 50 persons who
were diagnosed as suffering from this syndrome.
Question 47
If µ refers to the mean memory span of the population of persons suffering from Korsakoff's
syndrome, which of the following is an appropriate null hypothesis for testing the above prediction?
1. H0: µ < 7
2. H0: µ = 7
3. H0: µ ≠ 7

Question 48
Which of the following is an appropriate alternative hypothesis for testing the above prediction,
regarding the mean memory span of the population of persons suffering from Korsakoff's
syndrome?
1. H1: µ < 7
2. H1: µ = 7
3. H1: µ ≠ 7
Question 49
Testing the above prediction on a sample will require a - - - - - statistical test
1. non-directional
2. two-tailed
3. directional

Reasoning:
Directional is also one-tailed, while non-directional is two-tailed.
Question 50
A pharmaceutical company claims that a new sleeping pill which they are marketing will put people
to sleep in less than 15 minutes. A researcher wants to test see if the average time before people fall
asleep after using this pill matches this claim. She uses the following hypothesis:
H0 µ = 15 H1 µ < 15
Suppose she tests this on a random sample of n = 40 research participants who suffer from
insomnia. She finds that the mean time before members of the sample fall asleep after using the pill
is 14.3 minutes, with a standard deviation of 3.2. A subsequent t-test produces a two-tailed p-value
of 0.0345 and the level of significance was set at 0.05. What is the value of the one-tailed or
directional p-value?
1. 0.03450
2. 0.01725
3. 0.06900

Reasoning:
The two-tailed p-value is 0.0345, but because we have a directional alternative hypothesis, the
one-tailed p-value is 0.0345/2 = 0.01725

Question 51
A researcher wants to compare the mean of the non-verbal reasoning scores of a sample of n=25
students with that of the general population. According to the literature, the non-verbal reasoning
test which she uses was standardized to a population mean of µ = 100 and a population standard
deviation of σ = 10. What is the value of the standard deviation of the sampling distribution of the
mean, which will be required to calculate the Zẋ test statistic?
1. 0.4
2. 10
3. 2

Reasoning:
σ/√𝑛
10/5 = 2
Question 52
What does it mean to say, "the difference between the means of groups A and B is statistically
significant"?
1. The alternative hypothesis is valid

2. The alternative hypothesis should be rejected
3. The null hypothesis cannot be rejected

Reasoning:
When a result is statistically significant, the null hypothesis is rejected and the alternative
hypothesis is accepted.
A market researcher is asked to conduct a study to examine people's reaction to a movie trailer. He
draws a random sample of 20 males and 20 females who saw the trailer. He asks them to indicate
how likely it is that they will go and see the movie on a 7 -point scale, where 1 indicates 'not at all'
and 7 indicates 'definitely'. He wants to compare to establish whether males and females differ in
their intention to see the movie based on an exposure to the trailer.
Suppose the researcher finds that the mean and standard deviations for each group in the sample is
as follows:
Males ẋM = 5.7 SM = 2.1
Females ẋF = 4.19 SF = 1.6
Question 53
Which is the appropriate way to indicate the researcher's hypothesis which is to be tested?
1. H0 ẋM = ẋF H1 ẋM ≠ ẋF
2. H0 µM = µF H1 µM > µF
3. H0 µM = µF H1 µM ≠ µF


Reasoning:
Option 2 is incorrect, because the researcher wants to establish whether males and females
DIFFER in their intention (not indicating the direction – whether he expects males to have higher
intention)
• µ is the symbol for the population mean. (population in this case would be EVERYONE that
saw the movie trailer)
• ẋ is the symbol for sample mean. (the sample in this case is the randomly selected 20
males and 20 females)
Question 54
Which is the appropriate t-test statistic to calculate to evaluate the significance of the researcher's
hypotheses?
1. The t-statistic for the difference between the means of two independent samples
2. The t-statistic for the mean of a single sample
3. The t-statistic for the difference between the means of two dependent samples

Reasoning:
This is a matched pair-design, for every male, there is a female also tested, (that also watched the
trailer)
Question 55
A researcher is asked by a motivational speaker to establish whether a workshop on assertiveness

training is effective. The researcher decides to use a particular questionnaire which tests an
individual's level of assertiveness. He presents the questionnaire to each of a sample of 50
participants in the workshop before it begins and once again after it has ended to the same
participants. When analyzing these results, the researcher should use a statistical test for the
1. comparison of means for a single group

2. comparison of means for two dependent groups
3. comparison of means for two independent groups

Reasoning:
in no way affects, in any systematic way, the composition of the other sample. The two samples
come from two groups that have no obvious relationship.
On the other hand, the concept of dependent groups refers to situations where the samples are
related, and it implies that each subject in one group can be systematically paired off with a
subject from the other group.
Another example of a dependent design would be a repeated measures design, where the same
research participant is observed under more than one treatment or experimental condition. The
two sets of measurement (indicated by two variables – before the workshop, and thereafter) can
be regarded as two samples of data, which is to be compared to see whether some kind of change
has taken place.

Question 56
Which is a Type II error in statistical significance testing?
1. Rejecting the null hypothesis when it is in fact true

2. Not rejecting the null hypothesis when it is in fact false
3. Rejecting the alternative hypothesis when it is in fact true

Reasoning:
Question 57
Two samples may be regarded as independent when - - - - -
1. there is no systematic relationship between the composition of one sample and the other
2. they were drawn at different occasions
3. they are both totally random

Reasoning:
in no way affects, in any systematic way, the composition of the other sample. The two samples
come from two groups that have no obvious relationship.
Option 2 can refer to a repeated design, which is a dependent design.
Question 58
A sample of 70 people are tested on a test for assertiveness before and after a workshop in which
they are given assertiveness training. Which of the following is the most appropriate formula for
comparing the mean assertiveness score before the training with the one thereafter?

Reasoning:
tc (option 2) is calculated for independent samples.
td (option 3) is calculated for dependent samples.
THE T-TEST OF DIFFERENCES BETWEEN THE MEANS OF TWO DEPENDENT GROUPS (TD)

• When each subject in one sample is matched with regards to some characteristic to a
particular subject in the other sample
• two sets of scores – pre-training and post-training scores (before and after)
• pre- and post scores are correlated / dependent measures.
• Difference score ‘d’ = x1 (pre-training) minus x2 (post-training)
• D = population mean of difference scores
A researcher compares a sample of children from a special school for gifted children with a group of
children randomly drawn from other schools on a test which measures the creativity of the children
on a 9-polnt scale. She wants to know whether the children from the school for gifted children is likely
to have greater levels of creativity, planning to test at of α = 0.01
Based on the sample, she finds the following:
Sample
Sample Sample standard
Size mean deviation
Group 1 (gifted
children) 100 5.5 1.2
Group 2 (other
children) 300 4.9 0.8
All children pooled 400 5.1 1.0
Question 59
What is an appropriate alternative hypothesis for this research scenario?
1. H1 ẋ1 ≠ ẋ2
2. H1 µ1 ≠ µ2
3. H1 µ1 > µ2
Question 60
She calculates a t-test statistic of tc = 4.196 and uses a computer program to determine that p =
0.0002 for two-sided testing, which is highly significant. She is however concerned that this
significant result may be due to the relatively large sample sizes, so she decides to also calculate the
effect size to determine whether the result is meaningful irrespective of this.
ẋ1− ẋ2
She decides to calculate Cohen's d, using the formula d =
𝑠𝑝
The table below can be used as a guide to judge the practical importance of the result:

Practical
Effect Size Importance
Less than 0.4 Small
Beween 0.4 and 0.8 Medium
Greater than 0.8 High
Based on the calculated effect size, the researcher can conclude that the practical implication of her
finding is - - - - -
1. Small
2. Medium
3. Large

Reasoning:
5.5−4.9
d=
1
0.6
=
1
= 0.6 = Medium
Question 61
1. two variables measured on a nominal scale within a single group

2. two variables measured on a ratio or interval scale within a single group
3. two groups of subjects measured on an interval or ratio scale on a single variable

Reasoning:
A scatter plot is a graph that represents the measurements of two variables on two perpendicular
axes, usually called the x-axis (horizontal axis or abscissa) and the y-axis (vertical axis or ordinate).
Nominal or ordinal values does not reflect size or value.
Question 62
A researcher would calculate a correlation coefficient in order to establish - - - - -
1. the effect size of a statistical test where two means were compared for significance
2. the size of the relationship which exists between two continuous variables
3. whether a particular variable is distributed according to the z-distribution

Reasoning:
Correlation is a measurement of the extent to which two variables vary together.

Question 63
Which of the combinations of the options below can be substituted in the following sentence to
describe the situation when a significant negative correlation is found between two variables X and
Y?
A person who scores - - - - - on variable X is likely to have a - - - - - score on variable Y
1. low, low
2. low, high
3. high, high

Reasoning:
smaller. An example of a negative correlation might be age and health status: the older you get,
the less healthy you are likely to be.
Question 64
A researcher wants to establish whether the type of employment category that is filled by
employees of a particular company is significantly related to their gender. The employees can be
categorized as manager, human resources, administrative, maintenance or information technology
worker and the genders are male or female. Which would be the most appropriate test to use?
1. the t-test for two independent samples

3. the chi-square (‫א‬²) test statistic

Reasoning:
A TEST OF ASSOCIATION BETWEEN TWO NOMINAL (categorical) VARIABLES = PEARSON CHI-
SQUARE OF ASSOCIATION. Both job classification as well as gender is nominal (labels – just a
name, discrete – distinct and separate, mutually exclusive, difference is not measurable).
An appropriate test in this case would be the chi-square test of association, which is a general test
for determining whether two variables are distributed in the same way.
A group of hospitalized patients who have been diagnosed as suffering from dementia are treated
with certain drugs over a period of time. These drugs were prescribed to improve their mental
alertness. A researcher studies a random sample of 30 these patients who have been on these drugs
for varying amounts of time, hoping to establish a relationship between the number of days of drug
treatment and patients' scores on a Mental Alertness Test.
Question 65
Which is the correct formal way to express the appropriate null hypothesis for this research?
1. H0 ρ = 0
2. H0 µ = 0

3. H0 r = 0

Reasoning:
ρ is the symbol for the population correlation coefficient
r is the symbol for the sample correlation coefficient.
µ is the symbol for the population mean.
Question 66
Which is an appropriate test to determine the significance of the relationship between the number
of days that the drug was administered and the score on the Mental Alertness Test obtained by the
sample of patients?
1. The chi-square (‫א‬²) test

2. The test based on Pearson's product-moment correlation
3. A t-test for one sample

Reasoning:
The chi-square test is used when the variables are both nominal. Neither of these variables are
nominal.
Pearson’s product moment correlation is used to measure the linear relation between two
variables, that is, if one variable increases, the other variable will decrease/increase.
Question 67
What would the expected frequency in cell AX of the following contingency table be, if we were to
assume that the data in the cells in the table are distributed in a proportional way across the rows
and columns? (Rounded off to two places)
X Y
A 7 3
B 5 4
1. 0.37
2. 6.32
3. 7.00

Reasoning:
AX = (total of row A x total of column X)/column total + row total
AX = ((7+5)x(7+3))/(10+9)
AX = (12 x 10)/19
= 6.32

Question 68
If there is no relationship at all between two variables X and Y, what would be the most likely value
of Pearson's correlation coefficient r, out of the following?
1. -1.0
2. 0.5
3. 0.0

Reasoning:
Question 69
A contingency table represents - - - - -
1. the distribution of the frequencies for a variable

2. frequency counts for each of a number of possible outcomes of an experiment
3. the frequency counts if each outcome measured on two nominal-scale variables when they
are cross-classified

Reasoning:
Contingency tables are used to represent frequency counts of data that have been classified in
terms of 2 nominal variables (e.g., gender and occupational category). It is possible to fit ordinal,
interval or ratio scale measurements into such a table, but then has to be transformed into a
classification system, that is, the data have to be treated as if they represent nominal scale
measurements.
Question 70
Which of the values given below is the closest to the probable value of the Pearson's product
moment correlation coefficient for the variables X and Y?
Variable X 1 2 3 4 5 6 7 8
Variable Y 8 7 6 5 4 3 2 1
1. -1.0
2. 0
3. 1.0

Reasoning:

r= =
√𝑣𝑎𝑟 (𝑥)𝑣𝑎𝑟(𝑦) √[𝑛∑𝑥 2 −(∑𝑥)2 ][𝑛∑𝑦 2 −(∑𝑦)2 ]
8(120)−(36)(36) 960−1296
= =
√[8(204)−(36)2 ][8(204)−(36)2 ] √(1632−1296)(1632−1296)
−336
=
336
= -1
(Note that where the X values are inversed on the Y axis – i.e. 123, 321 – the answer is always -1)
All 4 exam papers in this document have this Pearson’s r question, with a variance between -1
(inversed), 0 (where there is a value of 0 in either row) or +1 (where the exact numbers follow, i.e.
123, 123)
Mock Exam 1
Questions 1 to 3 are based on the following case study
A psychologist want to determine the effect of locus of control on productivity in an information

technology company. She divides the personnel into two groups, those with an internal locus of
control and those with an external locus of control. She then uses job evaluation forms to assess the
actual work performance of the personnel in the two groups.
Question 1
The dependent variable in the study is - - - - -.
1. measured job performance

2. locus of control
3. job evaluation forms
Reasoning:
The dependent variable is the one that is predicted or explained. In this study the researcher tries
to predict work performance with the aid of locus of control.
Question 2
The independent variable in the study is - - - - -.
1. job performance
2. locus of control
3. job evaluation forms
Reasoning:
Locus of control is the independent variable because it is used to predict the dependent variable
(work performance).

Question 3
The study in the example illustrates a - - - - - design.
1. correlational
2. groups
3. combination of a groups and correlational
Reasoning:
In this study two groups (internal locus of control and external locus of control) are compared
with one another. It is therefore a groups design.
Question 4
Which of the following are advantages of studying statistical methods in psychology?
a) It leads to a better understanding of the content of psychological theories.

b) It helps us to evaluate the ethical claims of researchers.
c) It helps us to interpret the statistical significance of research results.
d) It gives insight into the nature of the scientific process.
1. (a) & (c)

2. (c)
3. (c), (b) & (d)
Reasoning:
The other alternatives are more general aspects of research and go beyond the statistical analysis
of the results.
Question 5
Consider the following statement: "That phase of sleep during which brain rhythms resemble those
of an alert person is called paradoxical sleep or rapid eye movement (REM) sleep". This statement is
a-----
1. conclusion based on empirical research

3. research hypothesis
Reasoning:
The statement gives a definition of REM sleep.
Question 6
A psychologist studies the effect that age has an attitude towards AIDS. She selects a sample of
subjects divided into three different age groups, 20-30 years, 30-40 years and 40-50 years. The three
age groups are:
1. different values of the variable age

2. operationalised definitions of the variable age

3. three different theoretical constructs

Reasoning:
In this study the variable ‘age’ is divided into three values.
Question 7
Which is of the following statements gives the best description of the goal of psychological research?
1. Logical reasoning based on controlled observation and measurement of human behaviour

2. Testing theories of human behaviour
3. Finding out what previous investigators have achieved with respect to a research problem
about human behaviour
Reasoning:
As explained on page 2 in the Guide. Psychological research is mainly concerned with testing
theories.
Question 8
Consider the following statement: "The experience of strong emotion is accompanied by

physiological reactions such as an increase in heart rate". This statement can be viewed as a
research hypothesis because it:
a. predicts a relationship between variables

b. makes and empirical prediction
1. (a) and not (b)

2. (a) & (b)
3. (b) and not (a)
Reasoning:
A psychological hypothesis is a relation between variables, and formulates a testable empirical
claim which usually involves postulating a relationship between two or more variables.
Question 9
A sport psychologist hypothesises that children with high levels of motivation will be more willing to
participate in soccer practice sessions (participation) than children with low levels of motivation. In
this study, the hypothesis is best described as expressing a - - - - -
1. relationship between two variables, ‘high motivation' and ‘low participation’.

2. A relationship between ‘low participation’ and ‘high participation’.
3. rule relating values of ‘motivation' to ‘participation’.
Reasoning:
As explained in the Guide, page 13 a hypothesis formulates rule expressing a relationship between
two or more variables. In this case the independent variable has two values, high and low
motivation.

Question 10
A psychologist uses a psychometric test to study the intelligence of school children. Intelligence is
the (a) - - - - - variable and the psychometric test represents the (b) - - - - - variable in this study.
1. (a) latent (b) theoretical

2. (a) manifest (b) operational
3. (a) latent (b) manifest
Reasoning:
Intelligence is a latent variable because it cannot be observed directly. The results of the
psychometric test can however be observed directly and can therefore be regarded as the
manifest variable.
Question 11
In the process of psychological research, researchers try to - - - - -.
1. prove that a theory is true

2. account for theoretical assumptions
3. obtain empirical support for a theory
Reasoning:
Theories can never be proved. Research psychologists are trying instead to find empirical support
for a theory.
Question 12
In the study guide, constructs are defined as:

1. (a) & (b)

2. (b)
3. (a), (b) & (c)
Reasoning:
All three statements are true
Question 13
The examination marks of statistics course yielded a normal distribution with a mean of 50 and a
standard deviation of 10. If you were to select the score of one student at random, what is the
probability that the score would be 60 or above?
1. 0,16
2. 0,34
3. 0,84


Reasoning:
The Z-score associated with 60 is (60-50)/10 = 1. The probability of a mark having 1 standard (i.e.
Z-score) above the mean is 0,16
Question 14
A ball is drawn at random from a box containing 6 red balls, 4 white balls and 5 blue balls. What is
the probability that it is red?
1. 2/5
2. 1/3
3. 0,5
Reasoning:
There are 6 + 4 + 5 = 15 balls and 6 of them are red. P(Red) = 6/15 = 2/5.
Question 15
Fill in the missing words to the quote: "Statistical methods may be described as methods for drawing
conclusions about - - - - - based on - - - - - computed from the - - - - -."
1. samples, parameters, population

2. parameters, statistics, population
3. populations, statistics, sample
Reasoning:
Populations are abstract and can usually not be studied directly. In research, samples are analyzed
and inferences are then drawn about populations on the basis of the statistics obtained from
samples.
Question 16
The sampling distribution of means refers to:
1. the distribution of the means of all possible samples of a particular size randomly selected
from the same population
2. the distribution of the different possible values of the sample means together with their
respective probabilities of occurrence
3. the distribution of the values of the items in the population
Reasoning:
Read the discussion of the distribution of sample means in the guide
Question 17
A standard normal distribution has a mean of (a) - - - - - and a standard deviation of (b) - - - - -.
1. (a) 1, (b) 16
2. (a) 50, (b) 1,5

3. (a) 0, (b) 1
Question 18
Which best describes the frequency distribution of the ages of students attending a particular class?
1. A graph of the ages of the students arranged from young to old

2. The total of all ages, divided by the number of students
3. The standard deviation of ages, indicating the width of the age distribution
Reasoning:
A frequency distribution will represent the number of students falling under each age group.
Question 19
A - - - - - Z score is above the mean while a - - - - - Z score is below the mean.
1. negative; positive
2. positive; negative
3. positive; zero
Reasoning:
Consider the formula for calculating a z-score in the guide. For a score that is larger than the mean
a positive z-score will be obtained. A score that is less than the mean will give a negative z-scores.
Question 20
What test score corresponds to a Z score of 1 if the mean and standard deviation of the scores are 5
and 2 respectively?
1. 7
2. 2
3. 5
Reasoning:
(7-5)/2 = 1.
Question 21
The Z score corresponding to a raw score represents the number of - - - - - that the raw score differs
from the mean of the raw score distribution.
1. points
2. standard deviations
3. percentiles
Reasoning:
Z-scores are standard deviations on the standard normal distribution.

Question 22
A table or graph showing how many subjects in a sample obtained each possible score on a test is
called a - - - - -.
1. probability sample
2. probability distribution
3. frequency distribution
Reasoning:
It is a frequency distribution.
Use the following summary of marks to answer Questions 23 and 24.
Subject Student X Mean of class Standard deviation of class
A 50% 40% 5%
B 55% 50% 5%
C 60% 50% 10%
D 65% 65% 5%
Question 23
In which subject did Student X do best, relative to his class?
1. A
2. C
3. D
Reasoning:
In the case of subject A, the student’s mark is 2 standard deviations above the mean. In the other
subjects the student’s marks are 1 standard deviation or less above the mean.
Question 24
In which subject(s) did Student X do worst, relative to the rest of his class?
1. A
2. B
3. D
Reasoning:
The student obtained marks higher than the mean for all the other subjects.
Question 25
The normal curve is asymptotic. This means that - - - - -.
1. it is symmetrical
2. it is bell shaped

3. the two tails never touch the horizontal axis

Reasoning:
The term ‘asymptotic’ is defined in the Guide.
Answer Questions 26 to 30 on the basis of the following scenario:
Sally claims that workers in large companies are less work motivated than workers in small
companies and plans to test her claim. In a previous study involving all large companies in South
Africa, it was found that the average motivation score on a work motivation questionnaire was 50
and that the standard deviation was 15. The higher a worker’s score on this questionnaire, the higher
the work motivation of the worker.
Question 26
What are the population parameters of interest?
1. μ and 0
2. μ and σ
3. μ and s
Reasoning:
The population of small companies’ mean score (μ is unknown) is compared to the population
means of the large companies (μ = 50). It is accepted that the populations have the same standard
deviation of 15.
Question 27
Which of the statistical hypotheses below reflect the research hypothesis to be tested?
1. H0 : μ = 50 H1 : μ > 50
2. H0 : μ < 50 H1 : μ > 50
3. H0 : μ = 50 H1 : μ < 50
Reasoning:
The claim is being made that small companies have a work motivation greater (>) than 50.
Question 28
In order to test the research hypothesis, Sally must compare two population distributions. Which are
these two distributions?
1. small companies and large companies

2. work motivation scores of small companies and large companies
3. work motivation scores of a sample of small companies and large companies
Question 29
What assumptions must Sally make?

1. The population distributions involved have the same shape

2. Both population distributions have the same standard deviation and shape
3. Both population distributions are normal and have the same variance
Reasoning:
Both population distributions are normal (which of course implies that they have the same form)
and have the same variance. Note that the standard deviation is merely the square root of the
variance.
Question 30
What is the sample statistic of interest?
1. The sample mean

2. The sample variance
3. The sample z-value
Reasoning:
The sample mean provides us here with an estimate of the population mean of small companies.
Question 31
Peter stated the following hypothesis:
H0: μ = 100
H1: μ < 100
He drew a random sample of 50 and obtained a mean score of 105. Given that the null hypothesis is
true, what is the reason why the mean of the sample is not exactly 100?
1. A type I error could have occurred

2. This is due to chance
3. The standard deviation caused this.
Reasoning:
Because our sample is selected randomly, there is always, a chance that the sample may not be
precisely representative of the population. We refer to this as sampling error.
Questions 32 and 33 are based on the following scenario:
Jennifer is testing whether certain food supplements increases the endurance of long distance
athletes. She randomly selects 20 athletes to take the supplements. She tests them with an exercise
routine for which the general long-distance population has a mean score of 50 minutes. She obtains a
mean score of 65 minutes for her test group.
Question 32
Which of the following statements represents the null hypothesis?
1. the mean score of the all long-distance athletes is 50 minutes

2. the mean score of the athletes taking the supplements is 65 minutes

3. the mean score of the athletes taking the supplements is 50 minutes

Reasoning:
Note that alternative 2 is incorrect, since 65 minutes is a sample result which is still unknown at
the stage when the null hypothesis is formulated. Note that alternative 1 is incorrect because it
does not refer to athletes who take supplements.
Question 33
If Jennifer rejects H0, it implies - - - - -
1. an acceptance of H1
2. that μ > 50
3. that a difference between sample means is a chance outcome
Reasoning:
Note that alternative 2 does not correspond to the research hypothesis. Jennifer expects that the
endurance of her athletes will be better and therefore that their average time will be less than 50
minutes and not more than 50 minutes.
Question 34
What does the H1: μ > 50 imply?
1. A relationship between two variables

2. A difference between two populations
3. Both 1 and 2.
Reasoning:
Note that all research attempt to establish whether a relationship exists between two or more
variables. Although we cannot infer from a statement such as H1: μ > 50 what two variables are
being referred to, we know that the researcher would have to have had such variables in mind if
he/she were to arrive at statistical hypotheses.
Question 35
How does one test an alternative hypothesis?
1. Decide whether H0 should be rejected or not on the basis of observations.

2. Compute the p-value for H1 and compare to the level of significance.
3. Consider whether the alternative hypothesis makes sense from a theoretical perspective.
Reasoning:
H0 and H1 are formulated in such a way that the rejection
of H0 implies the acceptance of H1.
Question 36
When is the null hypothesis equivalent to the research hypothesis?

1. When the research hypothesis implies no difference between the populations being
compared
2. When the null hypothesis states a difference in the means of the populations being
compared
3. When the research hypothesis is about the comparison of two population means
Reasoning:
The research hypothesis usually translates to the alternative hypothesis because it usually
suggests a difference between the population means.
It does happen though that the researcher wishes to suggest no differences between the
populations in which case the research hypothesis translates directly to the null hypothesis.
Question 37
The size of the level of significance depends on - - - - -
1. a choice made by the researcher

2. conventional rules
3. the p-value under H0
Reasoning:
conventional rules.
Question 38
A p-value is some value between - - - - -
1. 0 and 100
2. 0 and 0,05
3. 0 and 1
Reasoning:
If the p-value is expressed as a percentage, it may be a value between 0 and 100. It is not
customary to do so however.
Question 39
The null hypothesis is rejected if
1. the p-value is smaller than the level of significance

2. the p-value is larger than the level of significance
3. the p-value is smaller than the probability under H0
Question 40
Suppose study A and study B tests the same H0 and H1 and find the same z-test statistic value. Study
B consisted of a larger sample size however. We will probably find that - - - - -.

1. the p-value of study B is smaller

2. the p-value of study B is larger
3. the p-value of study A is equal to the p-value of study B
Reasoning:
The p-value is read from the z-tables for a specific z-value and the size of the sample does not play
a role here. In the calculation of the z-value, the size of the sample has already been taken into
account.
Question 41
Which one of the following is a way of increasing the power of a statistical test?
1. Increasing the sample size

2. Increasing the p-value in the decision rule
3. Decreasing the p-value in the decision rule
Reasoning:
The p-value may not be changed by the researcher and is determined by the data.
Question 42
A p-value gives the probability of a sample result under - - - - -.
1. H0
2. H1
3. The research hypothesis
Question 43
Whether a p-value is directional or non-directional depends on - - - - -.
1. the null hypothesis

2. the alternative hypothesis
3. null and the alternative hypothesis
Question 44
When analysing results, what do we call the hypothesis that the mean scores for two populations
are equal?
1. The scientific hypothesis

2. The null hypothesis
3. The alternative hypothesis

Question 45
Using a significance level of 0,05 in statistical hypothesis testing means that the probability of - - - - -
is at most 0,05.
1. making a Type I error

2. not making a Type I error
3. making a Type II error
Question 46
Which is true of the null and alternative hypotheses?
1. They can be both true, but not both false

2. They can be both false, but not both true
3. If one is true, the other must be false.
Question 47
Which is a Type II error in statistical significance testing?
1. Rejecting the null hypothesis when it is in fact true

2. Not rejecting the null hypothesis when it is in fact false
3. Rejecting the alternative hypothesis when it is in fact true
Reasoning:
Alternative 1 refers to the Type I error while alternative 3 is irrelevant because the statistical
decision rules apply only to the null hypothesis.
Question 48
Which of the following alternative hypotheses requires a two-tailed test of significance?
1. The correlation coefficient between test marks and examination marks for boys is different
from the same correlation for girls
2. The mean verbal ability score for boys is lower than the mean score for girls
3. The mean depression score after treatment will be lower than before treatment.
Reasoning:
Note that the statistical test procedure for comparing two correlations is not included in the
present syllabus but we can still judge that all that is proposed here is that two populations do not
differ with respect to their correlations between the same two variables. We are therefore only
able to formulate an alternative hypothesis that suggests a difference between the correlations
and therefore a two-tailed test of significance is indicated.
Question 49
The t test statistic is appropriate when - - - - -

1. The null hypothesis is about a sample mean and the population mean is unknown.
2. The null hypothesis is about a population mean and the population standard deviation is
unknown.
3. The null hypothesis is about a sample mean and the population standard deviation is
unknown.
Reasoning:
If the population standard deviation was known, a z-test would have been needed.
Question 50
Suppose a researcher is of the opinion that the proportion of Unisa students who are in favour of
group lectures are 0,5. He/she selects a single random sample of 144 Unisa students and find that 50
of these students are in favour of group lectures. If p = 0,5, what is the value of p, the sample
proportion?
1. 50/144
2. 144/50
3. (50/144 - 0,5)
Reasoning:
Sample proportion = 50/144.
Question 51
Suppose the zp value for the data in item - - - - - above is found to be 2,50. What is the value of the
p-value?
1. 0,4938
2. 0,0062
3. 0,0124
Reasoning:
The alternative hypothesis in Question 50 is clearly nondirectional. The p-value for a directional
test can be read directly from the z-tables as the area under the normal distribution to the right of
a z-value equal to 2,50 (Look under the column “smaller portion” in the z-tables). This p-value is
0,0062. The nondirectional p-value is therefore 2 x 0,0062 = 0,0124.
Question 52
Suppose the null hypothesis for the research problem in item 50 is rejected, what should the
research conclusion be?
1. The proportion of Unisa students that favour group lectures is not different from 0,5.
2. The proportion of Unisa students that favour group lectures is different from 0,5.
3. The proportion of Unisa students that favour group lectures is less than 0,5.
Reasoning:

If the null hypothesis is not rejected, alternative 1 would be correct. Alternative 3 cannot be
correct because the alternative hypothesis is nondirectional.
Question 53
An alternative hypothesis is described as: H1: μ1 > μ2
What does μ2 signify?
1. the sample mean of the second group sampled

2. the population mean of the second group sampled
3. the unknown parameter to be tested for under the null hypothesis
Reasoning:
The Greek character ‘mu’ or μ is used to indicate a population mean, as distinct from a sample
mean, which is indicated by 0. Note that one uses data from a sample to make inferences about
the population, so it is the population mean being tested for.
Question 54
The difference score d = X2 - X1 is used in the case of calculating - - - - -.
1. the t-test for comparing two independent samples

2. the t-test for comparing two dependent samples
3. the chi-square test
Question 55
To investigate the effectiveness of a motivational speaker, 50 members of his audience are randomly
chosen, and tested on a motivation scale before and after listening to his presentation. Which of the
following is the most appropriate statistical procedure to determine whether the motivational talk
made a difference?
1. the t-test for independent samples

2. the t-test for dependent samples
Reasoning:
The t-test is appropriate, and there is an implicit interdependence in data derived from repeated
measurements of the same variable for the same sample of subjects.
Question 56
In which of the following cases is it not appropriate to use the t-test for comparing means from two
samples?
1. the samples are large (200 cases each) but are not normally distributed
2. the samples are small (15 cases each) but are known to be normally distributed

3. the sample are small (10 cases each) but the distribution of the scores in the population is
unknown.
Reasoning:
Alternatives 1 and 2 both describe conditions under which the t-test may be used.
Question 57
A group of clerical workers are compared with a group of technical workers in a large company to
determine whether they differ in their levels of job satisfaction, using a t-test. Which would be the
dependent variable?
1. job category
2. job satisfaction
3. workers
Reasoning:
The way in which job category influences job satisfaction is being investigated, so it is job
satisfaction that depends on job category. While the whole population consists of workers, this is
not relevant to the research question.
Question 58
Which of the following test statistics may be used to compare proportions?
1. the z-statistic (zC)

2. the t-test statistic for independent samples (tC)
3. the t-test statistic for dependent samples (td)
Reasoning:
The z-statistic (zC) being the correct statistic for comparing proportions.
Question 59
Two samples may be regarded as independent when - - - - -.
1. there is no systematic relationship between the composition of one sample and the other
2. they were drawn at different occasions
3. they are both totally random
Reasoning:
It is a definition of independence for samples. Alternative 2 does not guarantee independence,
and alternative 3 is irrelevant.
Question 60
The size of the t-statistic for independent samples (tC) depends on - - - - -.
1. the two sample means of the variable being compared

2. the standard deviations from the two samples of the variable being compared


Reasoning:
Computation of the t-statistic depends on both means and standard deviations.
Question 61
Pearson's correlation coefficient r represents - - - - -
1. the size of the relationship between two variables

2. the shape of the relationship between two variables
Reasoning:
Pearson’s r indicates the extent to which a relationship is linear, so both size and shape is
relevant.
Question 62
Pearson's correlation coefficient r can take values ranging between - - - - -
1. 0 to 1
2. 1 to 10
3. -1 to 1
Question 63
A variable that can take only one of two possible values is called - - - - -
1. binomial
2. dichotomous
3. nominal
Question 64
If there is no relationship at all between two variables, what would be the most likely value of
Pearson's correlation coefficient r, out of the following:
1. -1,0
2. 0,5
3. 0,0
Reasoning:
If Pearson’s r = 0, there is no indication at all of a linear relationship. If there is ‘no relationship at
all’, there won’t be any linear relationship either.

Question 65
Which of the following does not represent a valid value for Pearson's r?
1. -0,72
2. 0,00
3. -1,01
Reasoning:
The smallest possible value of r is -1.
Question 66
A Pearson's correlation coefficient of r = 0,65 has been found. What kind of relationship between
two variables X and Y is implied?
1. as X gets larger, Y gets smaller

2. as X gets smaller, Y gets smaller
3. as X gets smaller, Y gets larger
Reasoning:
Alternatives 1 and 3 describe negative relationships. Since ‘as X gets smaller, Y gets smaller’
implies that as X gets bigger, Y gets bigger.
Question 67
A Pearson's correlation of r = 1,00 was found. What does this tell one about the relationship
between two variables X and Y?
1. they exhibit a strong absolute relationship

2. the relationship is perfectly linear
3. a relationship of r = 1,0 is impossible to achieve
Question 68
Which of the following tests are appropriate for determining whether a relationship exists between
two variables if both are measured on the nominal scale of measurement?
1. the t-test for two independent samples

2. testing the significance of the Pearson correlation coefficient
Reasoning:
The chi-square (χ2) test is to be used because the variables are nominal scale measurements.
Question 69
The chi-square test is used to compare which aspect of data for two samples?

1. the distributions of the data as classified in terms of a variable

2. the sample means of the variable for each sample
3. the variance of the variable as measured for each sample
Reasoning:
The chi-square test looks at the distribution of data over categories that may represent
measurements on the nominal level, and neither means nor variances are relevant to its use.
Question 70
A graphical representation of the relationship between two variables X and Y is called a - - - -
1. histogram
2. graph
3. scatter plot
Mock Exam 2
Question 1
Having read a recent publication of Watson’s theory about the nature of consciousness, a
student decides to conduct an experiment to critically examine aspects of the theory. The
main aim of the research will probably be to empirically - -
1) test predictions based on Watson’s theory
2) test Watson’s theory so that it can be accepted or rejected as a whole
3) study consciousness with a view to understanding, predicting and controlling it
Answer: Alternative 1 is correct.
Reasoning: The experiment is aimed at testing Watson’s specific theory and not
consciousness in general (alternative 3). Alternative 2 is incorrect because in the question
it is explicitly stated that the aim is to test aspects of the theory (and therefore not the
whole theory).
Question 2
A theory can be described as an interdependent set of - - - - - relations between - - -
1) proposed; constructs
2) empirical; hypotheses
3) verified; variables
Reasoning: A theory is defined as a “network of postulated relations between
constructs”. Alternative 2 is wrong because one does not test relations between
hypotheses, but between variables. The relations are postulated (and therefore not
verified) so that alternative 3 is also incorrect.
Question 3
Constructs are sometimes called - - - - -
1) indicators
2) referents

3) intervening variables
Refer: Study guide, pg. 3
Reasoning: See Study guide, page 3 where some synonyms of the term ‘construct’ are
mentioned.
Questions 4
Which of the following best describes “latent”?
1) observable
2) manifest
3) hidden
Reasoning: ‘Latent’ variables are not observable, but hypothetical or ‘hidden’.
Alternatives 2 and 3 are incorrect because ‘manifest’ and ‘observable’ mean the opposite
of ‘latent’ (i.e. variables that are NOT latent are manifest or observable).
Question 5
A measurement model of attention deficit disorder relates this - - - - - to its - - - - -
1) construct; intervening variables
2) hypothetical variable; observable instances
3) referent; manifestations
Answer: Alternative 2 is correct

Reasoning: This option is correct because (a) ‘attention deficit disorder’ is a hypothetical
variable used to refer to a cluster of observable symptoms, and (b) the symptoms are the
observable instances (of behaviour) which are used to measure (e.g. indicate the severity)
of the disorder. Alternative 1 is incorrect because one requires manifest, not latent
variables for measurement, and alternative 3 is also incorrect because a model is not just
a referent, but a theory of the relationship between ‘referents’ (or hypothetical entities).
Question 6
An operational definition defines a - - - - - in terms of - - - - -
1) manifest variable; observable behaviour
2) theoretical construct; observable consequences
3) observable construct; other constructs
Reasoning: Operational definitions are used to cross the gap between theory and
empirical research. It does this by describing theoretical constructs in terms of observable
instances, which can be measured and used to test a theory.
Question 7
Which best describes “research hypothesis”?
1) An empirically observed relation between two constructs
2) A proposed relation between two variables
3) A network of postulated relations between constructs
Answer: Alternative 2 is correct

Reasoning: A hypothesis posits a relation between two sets of variables, the independent
and the dependent variables (see page 8 in the study guide). Alternative 1 is incorrect
because the relation is theoretical or ‘hypothetical’ and not yet empirically investigated.
Alternative 3 is also incorrect because it defines the concept of a theory rather than just a
hypothesis (see Study guide page 4).
Use the following scenario to answer Questions 8 to 12:
“My explanation of acute stress disorder indicates how the intensity of stress is affected by
patients’ anxiety proneness, whether or not they received psychotherapy, and the nature of
the traumatic stressor. My research will investigate whether such patients’ level of anxiety is
actually reduced by psychotherapy. More specifically, patients receiving therapy are
expected to score lower on the Manifest Anxiety Scale than patients not receiving therapy.”
Question 8
“My explanation of acute stress disorder” is a - - - - -
1) scientific hypothesis
2) theory
3) postulated relation between two constructs
Reasoning: The explanation is a theory because it presents a postulated relation between
a set of constructs (i.e. type of stressor, intensity of stress, anxiety proneness).
Alternative 1 is incorrect because the scenario provides a general explanation of the
relations, but not a specific hypothesis that has been formulated for testing.
Alternative 3 is also incorrect because the explanation involves a relation between
more than two constructs.
Question 9
“Patients’ level of anxiety is reduced by psychotherapy” is - - - - -
1) an observed relation between two variables
2) a theoretical hypothesis
3) an operational hypothesis
Reasoning: A specific hypothesis is now derived from the theory presented in the
scenario. Alternatives 1 and 3 is incorrect because the terms ‘level of anxiety’ and
‘psychotherapy’ have not been operationally defined in the statement given.
Question 10
The dependent variable(s) in my research is/are - - - - -
1) anxiety proneness, nature of the traumatic stressor, and psychotherapy
2) whether or not psychotherapy is received
3) level of anxiety experienced by patients
Reasoning: In the hypothesis mentioned in Question 9 it is indicated the level or intensity
of anxiety experienced ‘depends’ on other variables such as anxiety proneness and
psychotherapy received, showing that it functions as a dependent or Y-variable which is
to be predicted or explained in the study.

Question 11
The independent variable in my research is - - - - -
1) whether or not psychotherapy is received
2) level of anxiety experienced by patients
3) the intensity of stress

Reasoning: In the study it is predicted that psychotherapy will have an effect on the level
(i.e. intensity) of anxiety experienced. It is therefore an independent variable which can
be placed in the position of the variable X.
Question 12
When interpreting the results of this research I will assume that anxiety proneness
and the nature of the traumatic stressor - - - - -
1) do affect level of anxiety, but their effects more or less cancel out over all my
patients
2) do not affect level of anxiety
3) do affect level of anxiety, but according to the central limit theorem their average
effect will be zero
Reasoning: It is obvious that the type of stressor may have an effect on the level of
anxiety experienced, but if an unbiased (e.g. random) sample is selected from the
population, the influence of the type of stressor will be averaged over the sample.
Alternative 2 is incorrect because there are no grounds for assuming that the type of
stressor will not affect anxiety. Alternative 3 is also incorrect because the central limit
theory is not applicable here (it refers to the nature of the sampling distributions of
sampling statistics and not to the value of specific variables).
Question 13
A class of 10 boys and 11 girls, including Mary and her friend Elizabeth, chooses a class
representative by writing their names on slips of paper, putting these into a box and asking
their teacher to draw one name blindly. What is the probability that Mary will be selected?
1) 1/11
2) 1/20
3) 1/21
Reasoning: We need to calculate P(Mary is elected) = favourable outcomes/possible
outcomes = 1/(11+10) = 1/21.
Question 14
Which statement best represents an application of the law of large numbers? If I flip a coin
1000 times it will fall heads up - - - - - 500 times.
1) approximately
2) exactly
3) at least

Refer: See Study guide, page 27.

Reasoning: The law of large number states that the number of heads will converge on
(i.e. approach) the theoretical probability of 0,5., and not that it will reach it exactly
(alternative 2).
Question 15
Which of the following does NOT represent a probability?
1) 99%
2) 0
3) -0,05
Answer: Alternative 3 is incorrect.
Refer: Study guide, page 28
Reasoning: By definition probabilities fall within the range 0,00 and 1,00 and can
therefore never have a negative value.
Question 16
The expression “0,05 < p < 0,10" denotes a probability value - - - - -
1) somewhere in the range 0,05 to 0,10
2) larger than or equal to 0,10; or smaller than or equal to 0,05
3) larger than 0,05 and smaller than 0,10
Reasoning: The expression states that p can be equal to or larger than 0,05, and equal to
or smaller than 0,10, indicating that the range includes 0,05 and 0,10. Alternative 2 is
incorrect because it allows p to be larger than 0,10 and smaller than 0,05. Alternative 3 is
also incorrect because it does not specify that p can be equal to 0,05 or 0,10 as well.
Question 17
If 5000 students wrote an exam, 3000 passed with 50% or more and 250 obtained exactly
50%, what is the value of p (% score greater or equal to 50|pass) for randomly selected
students?
1) 0,025
2) 1/12
3) 1

Reasoning: The formula p (% score greater or equal to 50|pass) should be read as the
conditional probability of someone obtaining 50% or more and that someone passing. It is
clear from the example that any student selected from the given population who
obtained 50% or more, has necessarily also passed. The probability is therefore 1.
Question 18
Use the following frequency distribution of 1000 scores on a subscale of an intelligence test
to answer the question.
Score (X): 11 12 13 14 15 16 17 18
Relative frequency (%): 4 11 13 22 18 17 9 6

The value of p(X larger than or equal to 18) is - - - - -

1) 0,06
2) 0
3) 94%
Reasoning: Looking at the table we notice that only 6% of the students obtained a score
of 18 (and none higher than this). The probability of obtaining a score equal to or higher
than 18 is therefore 6%, which is equal to 6/100 or 0,06.
Question 19
During the interpretation of psychological measurements the normal distribution is - -
1) adapted to fit the observed frequency distribution of scores
2) used as a theoretical model for interpreting the observed distribution of scores
3) used to calculate the relative frequency of observed scores
Reasoning: The normal distribution is a theoretical distribution which is used to
determine the probability of a given score provided the mean and standard deviation are
known. It is not dependent on observed frequencies (alternative 1), nor is it used to
calculate the relative frequency of observed scores (alternative 3) which can only be
obtained empirically.
Question 20
The scale along the X-axis of the standard normal distribution indicates - - - - -
1) probabilities
2) the mean of the distribution
3) the number of standard deviations below and above the mean
Reasoning: The standard normal distribution is a normal distribution divided up into
intervals of standard deviation on the X-axis
Question 21
The area under the standard normal curve equals - - - - -
1) its mean
2) its standard deviation
3) one
Refer: See figure 2.5 in the study guide and the explanation on pages 34 and 35.
Reasoning: The standard normal curve defines a probability distribution ranging from 0 to
1 inclusive.
Question 22
The mean and standard deviation of a set of test scores are 20 and 8 respectively.
What is the z-score corresponding to a test score of 14?
1) 6
2) 0,75
3) -0,75


Reasoning: To calculate the z-score, we use the formula in the study guide. If we insert
the values given into the formula, we obtain (14-20)/8 = - 6/8 = - 0,75.
Question 23
Joseph scores 60% in a History test (class mean 65%, standard deviation 10%) and 50% in a
Biology test (class mean 53%, standard deviation 12%). Use z-scores to decide which
statement is true: Relative to the rest of his class Joseph does - - - - -
1) better in Biology than in History
2) better in History that in Biology
3) equally well in History and Biology

Reasoning: Joseph’s z-score for History is (60-65)/10 = -0,5, and for Biology it is (50-3)/12
= - 0,25. His marks for both subjects were below the mean, but because -0,5 < -0,25 it is
clear Joseph’s z-score for History places him further to left of the mean on the standard
normal distribution than his z-score for Biology. This means that he did worse in History
than in Biology relative to the rest of the pupils in his class.
Question 24
The sampling error of the mean will be smaller in cases where the - - - - -
1) sample is larger and the standard deviation of the population smaller
2) population is larger and the variability of the scores in the sample is smaller
3) sample mean is smaller
Reasoning: As mentioned in the study guide, the sampling error involves dividing the
population standard deviation by the sampling size, which means that the error will
decrease necessarily when the standard deviation becomes smaller (the numerator), and
the sampling size increases (the denominator).
Question 25
The central limit theorem implies that, for large samples from non-normal populations, - - - -
1) the sampling distribution of the mean will be approximately normal
2) the distribution of sample values will be approximately normal
3) the observed relative frequency of an event will approach its theoretical probability
Reasoning: See the definition and brief explanation of the central limit theory in the study
guide.
Base your answers to Questions 26 to 28 on the following scenario.
Suppose that the memory span of adults is normally distributed with a mean of 7 items and
a standard deviation of 2 items. A researcher predicts that “dyslexic adults have a shorter
memory span than adults in general”.

Question 26
Which of the following is an appropriate null hypothesis for testing the above prediction?
1) The mean memory span of the population of dyslexic adults is smaller than 7
2) The mean memory span of the population of dyslexic adults equals 7
3) The mean memory span of the population of adults equals 7
Answer: The correct alternative is 2.
Reasoning: The null hypothesis here is μ = 7.
Question 27
Which of the following is an appropriate alternative hypothesis for testing the above
prediction?
1) The mean memory span of the population of dyslexic adults is smaller than 7
2) The mean memory span of the population of adults is not equal to 7
3) The mean memory span of the population of dyslexic adults equals 7
Reasoning: The alternative hypothesis here is μ < 7 because that would imply that the
“dyslectic adults” score worse than the normal adults and this is what the researcher is
predicting will be the case.
Question 28
Testing the above prediction will require a - - - - - statistical test.
1) non-directional
2) two-tailed
3) directional
Reasoning: This is because of the symbol “<“ in the alternative hypothesis
statement. If this symbol had been “≠” then a non-directional test would be required.
Question 29
Statistical hypotheses are statements about - - - - -
1) population parameters
2) sample statistics
3) both of the above

Reasoning: Note that the alternative and null hypotheses here are about the value of μ
which of course is a population parameter.
Question 30
The sampling distribution of a statistic (e.g. of the sample mean) can be calculated if we
assume that the - - - - - hypothesis is true, but not if we assume that the - - - - - hypothesis is
true.
1) null; alternative
2) alternative; null
3) statistical; research

Reasoning: We derive the sampling distribution of the statistic under H0 (as if H0 is true
Question 31
When applying a statistical test, the p-value represents the probability of obtaining
the - - - - -
1) sample statistic under the alternative hypothesis
2) population parameter under the null hypothesis
3) sample statistic under the null hypothesis
Reasoning: The p-value is an area below the sampling distribution of the statistic (or test
statistic). We saw that such a sampling distribution can only be derived under H0.
Question 32
When a statistical test yields a large p-value, which of the following statements is most
correct?
1) The alternative hypothesis is probably true
2) The null hypothesis is probably false
3) The null hypothesis is probably true
Reasoning: Note first of all that the p-value is concerned with how probable the sample
result is given that the null hypothesis is true. Now if the p-value is small, we begin to
suspect that the null hypothesis may be false and should be rejected. If the p-value is
large on the other hand, the null hypothesis is probably true.
Question 33
Suppose we have stated H0: μ = 10, and H1: μ < 10, and find that the sample mean
corresponds to a z-score of -3. This means that the corresponding p-value - - - - -
1) need not be found to reach a decision
2) is 0,0026
3) is 0,0013
Reasoning: We know that a z-scores of -3 (look in the z-tables) are extremely unlikely. We
also know that the negative sign indicates that H1 has a logical chance of being correct
instead of H0 (the result is in the correct direction). This result of -3 is highly unlikely under
H0 and H0 should be rejected in favour of H1. This all means that we need not find the p-
value because we know it will be very small.
Question 34
The hypothesis “H1: μ < 30" is a - - - - - hypothesis and requires a - - - - - statistical test.
1) non-directional; one-tailed
2) directional; two-tailed
3) directional; one-tailed
Reasoning: See answer to question 28.

Question 35
When applying a z-test to compare a sample mean to a known population mean, what do
we call the calculated z-value?
1) A test statistic
2) A sample statistic
3) A population parameter
Question 36
When applying a z-test to compare a sample mean to a known population mean, the p-
value represents the probability of - - - - -
1) correctly rejecting the null hypothesis
2) obtaining the sample mean under the alternative hypothesis
3) obtaining the sample mean under the null hypothesis
Question 37
Which statement is true of the level of significance of a statistical test?
1) It is based on the p-value of the test statistic
2) It is often selected in advance by the researcher
3) It is the probability of obtaining the sample statistic under the null hypothesis
Reasoning: The level of significance is a kind of “benchmark” p-value against which the
researcher will compare the actual p-value of his test statistic.
Question 38
When applying a statistical test, a decision is reached by comparing the - - - - - to the - - - - -
1) p-value; level of significance
2) test statistic; population parameter
3) test statistic; level of significance
Question 39
When applying a statistical test, if the p-value is larger than the level of significance we - - - -
the null hypothesis.
1) accept
2) do not reject
3) reject
Reasoning: We also sometimes say “fail to reject H0" or “retain H0". This may appear to be
the same as “accepting H0” but is not. The reason is that the testing of the null
hypothesis begins by accepting H0. We can now either reject it or fail to reject it but we
cannot, on the basis of the sample result, accept it. In practise many researchers do not

make a distinction between “accept” and “not reject”. We need not go into the precise
philosophical reasons.
Question 40
When applying a statistical test, if the p-value is larger than the level of significance
we - - - - - the alternative hypothesis.
1) do not accept
2) fail to reject
3) accept
Reasoning: We can only accept the alternative hypothesis if we reject the null hypothesis.
The null hypothesis can only be rejected for p-values smaller than the level of
significance. For a p-value larger than the level of significance we cannot reject H0 which
means we cannot accept H1.
Question 41
When applying a statistical test, the probability of a type I error is equal to - - - - -
1) 0,05 or 0,01
2) the p-value of the test statistic under the null hypothesis
3) the p-value of the test statistic under the alternative hypothesis

Reasoning: The researcher sets the level of significance in advance. Although it is often
0,05 or 0,01 it can be any value. The level of significance gives directly the maximum type
I error the researcher is willing to risk. He/she may perform several statistical tests with
associated p-values. These p-values give the exact probability of a type I error for a
particular statistical test performed whereas the level of significance gives the maximum
probability of a type I error the researcher is willing to make. When the question asks
about the probability of a type I error of a study in general, the answer is given by the
level of significance. But when the question asks about the probability of the type I error
of a specific statistical test performed, the answer is given by the p-value.
Question 42
1) rejecting the null hypothesis
2) a type I error
3) a type II error
Reasoning: We know that the type I error that a researcher is willing to make is controlled
by the researcher by setting the level of significance (α) in advance. The probability of a
type II error (β) is not controlled in advance by the researcher except for the fact that we
know that the lower (smaller) the probability of a type I error (α) the greater (larger) the
probability of a type II error (β).
Question 43
The natures of the research process and of statistical analysis are such that statistically
significant results are - - - - -

1) also psychologically important

2) psychologically important if a high level of significance was used
3) not necessarily psychologically important
Question 44
A researcher draws a single random sample from a population to test his hypothesis about
the mean population score on a psychological test. Scores on this test are distributed
normally in the general population with a known mean but an unknown standard deviation.
Which test statistic should the researcher calculate to test his hypothesis?
1) The t-statistic for the mean of a single sample
2) The z-statistic for the mean of a single sample
3) The standard deviation of the sampling distribution of the mean of a single sample
Reasoning: As a single sample mean is involved but the population standard deviation is
unknown, the appropriate test statistic is a t-statistic for a single sample mean.
You wish to test the hypothesis that the majority of persons aged 70 years or more are
females. Using registers of pensioners you obtain a random sample of 250 persons aged 70
or more and find that 150 of them are female.
Question 45
Which are the appropriate statistical hypotheses for the analysis of your result?
1) H0: P equals 0,5; H1: P is larger than 0,5
2) H0: μ equals 70; H1: μ is larger than 70
3) H0: P equals 0,5; H1: P is not equal to 0,5
Reasoning: Note that H0 states that half of the population (70-year olds) are female (P=
0,05) which implies that half (P= 0,05) are men. H1 simply states that more than half (P =
0,5) of the population (of 70-year olds) are female.
Question 46
Which research design did you use?
1) A correlational design with variables measured on a nominal scale
2) A two-group design with measures of age and gender
3) A single-sample groups design

Reasoning: Only a single variable is involved namely gender. A single sample is selected
and the statistic of interest is “the proportion of females”. In a correlation design a single
sample is also selected but there will be at least two variables between which the
researcher wishes to show a relationship.
Question 47

1) The z-statistic for a sample proportion

2) The z-statistic for the mean of a single sample
3) The t-statistic for the mean of a single sample
Question 48
What are the requirements with regard to statistical testing of the results?
1) A one-tailed statistical test should be performed
2) A two-tailed statistical test should be performed
3) No statistical test is required
Reasoning: A one-tailed test is required as the alternative hypothesis suggests that the
proportion of females is greater than 0,5. The sample proportion is 150/250 = 0,6, the
result is therefore in the right direction (as indicated by the alternative hypothesis) and a
one-tailed statistical test will be required to find out if the result is statistically significant.
To validate a new depression scale a researcher applies it to 50 patients diagnosed with

depression and 50 patients diagnosed with stress. She predicts that the depression sample
will score higher (more depression) than the stress sample. The mean scores of the two
samples are found to be 30 (standard deviation 10) and 25 (standard deviation 10)
respectively.
Question 49
Which is an appropriate null hypothesis for the analysis of the results?
1) μ1 = μ2
1) μ = 25
2) The population mean of the difference score equals zero
Reasoning: The null hypothesis is the hypothesis which states that there is no group
effect, in other words, no difference between the two groups. Alternative 2 refer to the
testing of a single sample size, and are not relevant to comparing two samples. The
difference score as referred to in Alternative 3 is used when the two samples are
dependent, for example, testing a sample of subjects before and after some event, which
is not the case in this example.
Question 50
Which research design did the researcher use?
1) Single-sample groups design
2) Two-sample groups design
3) Two-sample correlational design
Reasoning: There are two samples, each drawn from a different group (people suffering
from stress and people with depression). Correlations are used to show the degree of
linear relationship between two variables from a single sample, so Alternative 3 is not
appropriate.

Question 51
Which of the following assumptions underlies the calculation of the test statistic?
1) The population standard deviation is known
2) The two populations have different means
3) The two populations have the same variance
Reasoning: That the two populations from which the samples were drawn have the same
variance is a general assumption of the t-test for independent samples. It is, however, not
necessary for the population standard deviation to actually be known (as suggested in
alternative 1). The possibility that the two populations have different means (Alternative
2) is not an assumption, it is this that is being tested for by performing a statistical test.
Question 52
To test the efficacy of psychotherapy aimed at relieving depression, a researcher applies a
depression scale to 50 depressed patients at the start and again at the end of their
treatment, predicting that the latter scores will be lower (reflecting less depression). Scores
on his depression scale among the general population have a mean of 30 and a standard
deviation of 10. Which research design is appropriate to test the research hypothesis?
1) A two-sample groups design with independent groups
2) A two-sample groups design with dependent groups
3) A one-sample groups design
Reasoning: The two sets of measures obtained are dependent measures and therefore
the design is for dependent groups.
A teacher investigates the effect of extra classes on the performance of pupils in

mathematics. A group of 20 pupils receives the extra classes while a control group of
20 pupils receive singing lessons. For each of the 40 pupils the teacher calculates the
increase or decrease in his or her mathematics performance by comparing the marks
obtained in an examination before the extra classes to the marks obtained in an examination
after the extra classes.
Question 53
Which is the most appropriate research hypothesis for the teacher to test?
1) The mean mathematics score after the extra classes is larger than before the extra
classes for the experimental group
2) The mean mathematics difference score (after minus before) of the experimental
group is larger than that of the control group
3) The mean mathematics score after extra classes is higher for the experimental group
than for the control group
Answer: Alternative 2 is the only hypothesis that takes account of all the information.
Reasoning: The before and after scores are summarized into a difference score (after
minus before), and the two groups are then compared with regard to the change in
difference scores. The intervention (extra classes) can be judged as being successful if the

difference scores of the control group does not change much (so the difference score
should be close to zero), but the experimental group should show a positive change in the
difference score due to the effect of the extra classes. Alternative 1 looks only at change
in the scores of the experimental group, and alternative 3 compare the two groups only
after the intervention. Note that the hypothesis stated in alternative 3 would be
equivalent to that stated in alternative 2 if we knew that the two groups were equal in
their mathematics performance before extra classes commenced. But we do not know
this of course.
Question 54
Which is the appropriate test statistic to be calculated when analysing the results of this
research?
1) The t-statistic for the difference between the means of two independent samples
2) The t-statistic for the difference between the means of two dependent samples
3) The t-statistic for the mean difference score of a single sample
Reasoning: There are two samples (experimental and control group) which can be
regarded as independent (there is no particular relationship between them).
Question 55
The probability under the null hypothesis of obtaining a t-value of 2,5 or higher in the case
of a one-tailed test is - - - - - that for a two-tailed test.
1) the same as
2) twice
3) half
Answer: The correct Alternative is 1.
Reasoning: A two-tailed p-value (used in the case of a non-directional hypothesis) is twice
the size of a one tailed p-value (see page 66 of the study guide); or, conversely, a one-
tailed p-value (used in the case of a directional hypothesis) is half the size of a two-tailed
probability.
A marriage counsellor expects that second marriages more often end in divorce than first
marriages. She tests this hypothesis by following up 200 marriages that were all registered
five years ago, 50 in which at least one partner had been married before and 150 in which
neither partner had been married before. Of the 150 first marriages 30 ended in divorce; of
the 50 second marriages 10 ended in divorce.
Question 56
Which constructs feature in the researcher’s hypothesis?
1) Type of marriage (first/second); divorced (yes/no)
2) First marriage; second marriage; divorced (yes/no)
3) First marriage; second marriage; divorced; not divorced
Reasoning: A construct is a single meaningful unit or concept that can be measured on
some kind of a scale (when it becomes a variable). The researcher in the example is

comparing a single construct with two possible states (type of marriage) with a second
construct, also with two possible states (divorced or not). The alternative 2 implies that
the first and second marriage is two separate things (variables), and alternative 3 extends
this to having been divorced or not.
Question 57
A politician asks his audience of 100 whether they will vote for him, and 60 say yes. He then
delivers his speech and repeats the question. Now 70 persons say yes. When analysing these
results the two sets of answers should be regarded as - - - - -
1) dependent
2) independent
3) having been drawn from the same population
Reasoning: The measurements can be regarded as repeated measurements within the
same overall sample, which implies a systematic relationship.
Question 58
In correlational research one investigates the relation between - - - - -
1) the mean of a single sample of subjects and a population mean
2) two groups of subjects, with respect to a single variable
3) two variables measured on the same group of subjects
Reasoning: A correlation is a statistic that shows the size of a relationship between two
variables for a sample of subjects, so alternative 3 is the correct answer. It cannot be used
to show the relationship between two groups of subjects on a single variable as suggested
in alternative 2, nor is it related to the comparison between sample and population
means, as suggested by alternative 1.
Question 59
1) two variables measured on a nominal scale within a single group
2) two variables measured on a ratio or interval scale within a single group
3) two groups of subjects with regard to a single variable measured on an interval or
ratio scale
Answer: The correct answer is alternative 2.
Reasoning: Alternative 1 cannot be true because, in the case of nominal scale
measurements, numbers are allocated to subjects on the basis of their membership to a
category (for example, diagnostic categories in psychopathology like ‘schizophrenic’,
‘depressive’, ‘bipolar’, etc.), but the actual numbers allocated are arbitrary. It is not
possible to represent this on a continuous measurement scale as is required for a scatter
gram. Alternative 3 is also false, because a scatter gram shows a graphical representation
of a relationship between two variables for a single group of subjects, not between two
groups of subjects.
Question 60
A positive correlation between variables X and Y implies that persons scoring low on X will
generally score - - - - - on Y.

1) high
2) low
3) either high or low
Answer: The correct answer is alternative 2.
Reasoning: A positive correlation implies that as one variable changes, the other changes
in the same direction. A high value on X will imply a high value on Y, while a low value on
X will be matched by a low value on Y.
Question 61
Which of the following can take on a value of -0,5?
1) a probability
2) a level of significance
3) a correlation coefficient
Answer: The correct answer is 3.

Reasoning: Probabilities and levels of significance cannot take on a negative value.
Question 62
What is the correlation coefficient between the following values of X and Y?
X -2 -1 0
Y -2 -1 0
1) -1
2) 0
3) +1
Reasoning: X and Y are the same, which implies a perfect positive (+) correlation, and the
highest possible value that a correlation coefficient can reach is 1.
Question 63
A researcher hypothesizes that the drug treatment of hospitalised schizophrenic patients
improve their mental alertness. He studies a random sample of 27 such patients and finds a
correlation coefficient of 0,6 between the numbers of days of drug treatment and patients’
scores on the Mental Alertness Test. Which is an appropriate null hypothesis for this
research?
1) ρ = 0
2) μ = 0
3) P = 0
Reasoning: The symbol ‘ρ’ represents the population parameter being tested when you
calculate the Pearson’s correlation coefficient ‘r’; that is, you calculate r for the sample,
then have to decide whether this is likely to represent a significant correlation for the
whole population, by looking at the level of significance (the p-value). In a similar way ‘μ’
represents the population parameter (statistic) for a mean, and ‘P’ the population
parameter for a proportion.

Question 64
A researcher obtains a correlation coefficient of 0,40 between IQ scores and examination
marks in a random sample of 10 PYC 3704 students, and again a correlation coefficient of
0,40 between the same two variables on another random sample of 100 PYC 3704 students.
Which of these two correlation coefficients is the more likely to differ significantly from zero
under the null hypothesis?
1) That obtained on the smaller sample
2) Both are equally likely to be significant
3) That obtained on the larger sample
Reasoning: The larger the sample, the less likely that the variables will be correlated
purely by chance. So, a smaller value of the correlation coefficient (Pearson’s r) is needed
in order to reach significance for a larger sample.
Question 65
A contingency table is used to summarize the relationship between two variables measured
on - - - - - scale.
1) a nominal
2) an ordinal
3) an interval or ratio
Answer: Alternative 1 is the correct answer.

Reasoning: Contingency tables are used to represent frequency counts of data that have
been classified in terms of 2 nominal variables (e.g., gender and occupational category). It
is possible to fit ordinal, interval or ratio scale measurements into such a table, but then
has to be transformed into a classification system, that is, the data have to be treated as if
they represent nominal scale measurements.

List of formulae

Appendix: Probabilities associated with the standard normal distribution (z)

Appendix: Probabilities associated with the standard normal distribution (z) continued

Appendix: Probabilities associated with the standard normal distribution (z) continued

Appendix: Probabilities associated with the standard nom\at distribution (z) continued
Multiple-choice questions and solutions
Test Yourself Questions from Study Guide

Topic 1
In each of the following statements of a research problem, identify which one is the dependent and
which one the independent variable:
a) Couples who are willing to openly discuss their feelings, have more stable marriages.
Remember, the independent variable (x) affects the dependent variable(y); {x  y}
Here, `willingness to discussing feelings' is supposed to have an effect on `stability of marriage'.
Therefore `stability of marriage' is the dependent variable and `willingness to discussing feelings'
is the independent variable.
b) Men are more likely to be aggressive than women.

In this statement, the claim is made that èxpression of aggression' is affected by `gender', so
gender is the independent variable on which the expression of aggression (the dependent
variable) depends.
c) People who were abused as children are more likely to abuse their own children than people
who were not abused as children.
In this statement the claim is made that the predisposition to abuse one's children (the dependent
variable) is dependent on whether one was abused as a child (the independent variable).
Questions:
1. Inferential statistics is a branch of statistics concerned with ...
1) inferring numerical properties of sample data.
2) inferring properties of samples from assumptions.
3) estimating properties of populations from data.
Option 3 is correct.
Note that 1 and 2 are incorrect because we calculate statistics for samples and then make
inferences concerning population parameters.

2. Research in psychology is primarily about ...

1) gathering facts.
2) testing theories of human behaviour.
3) making assumptions.
Options 1 and 3 are not altogether wrong, but 2 is more correct. We do make assumptions in
research, but this is not the essential goal of research.
3. The main purpose of psychological research is to ...

1) test theories empirically.
2) select random samples.
3) apply inferential statistics.
Again, although we do select samples (option 2) and apply inferential statistics (option 3), these
are not as general an aim of research as is option 1.
4. A theory is a network of ...

1) relations among facts that were proven to be true.
2) explanations for observed phenomena in terms of constructs.
3) hypotheses that were observed.
Option 1 would also have been correct if the word `proved' had been replaced with `proposed'.
Option 3 is obviously incorrect as hypotheses are theoretical in nature.
5. Constructs are ...

1) theoretical in nature.
2) empirical in nature.
3) identical to variables.
It is correct because we know that constructs are abstract concepts proposed by the researcher
for scientific use. Option 2 is incorrect as èmpirical' means the opposite of theoretical. Although
we indicated that we would use the terms `constructs' and `variables' interchangeably, these two
terms are not identical. Strictly speaking, the latter term refers to constructs that have been
measured.
6. An item in a psychological test may be considered to be a ...

1) manifest variable.
2) test construct.
3) both of the above.
Option 2 makes no sense: constructs are usually abstract concepts that cannot be observed
directly.
7. Constructs such as anxiety can be ...

1) observed directly.
2) empirical in nature.
3) defined in terms of behaviour.

Option 3 is the more correct answer.

Options 1 and 2 are incorrect because constructs cannot be observed directly and the word
èmpirical' refers to things or events that can be observed.
8. Operational definitions of psychological constructs should define constructs ...

1) in terms of observable behaviour.
2) in terms of other constructs.
3) through measurement.
The correct answer is option 1.
Option 2 is incorrect because `òperational'' refers to practical procedures by which constructs are
made visible. Constructs are often explained in relation to other constructs, but this is not an
òperational' definition. Option 3 is incorrect because, although the defining of constructs in terms
of observable behaviour leads to measurement, it is not identical to the measurements.
9. Operational definitions enable us to ...

1) bridge the gap between theory and observations.
2) observe constructs.
3) do both of the above.
Option 3 is correct because both 1 and 2 are correct.
Operational definitions link constructs to observable phenomena so that we can observe them.
10. The nature of an hypothesis refers to a rule that tells us ...

1) which variables cause, or are associated with, which variable.
2) which value of an independent variable is associated with which value of a dependent
variable.
3) the nature of the variables as constructs.
Option 1 is incorrect because, although hypotheses are about variables, they are about the
relation between the variables, not about causes. The nature or rule of the relation is about how
the independent variable relates to the dependent variable. An hypothesis is a statement of
relationships among variables, not about the nature of variables, so option 3 is not correct.
11. Suppose an hypothesis states that X causes Y. We cannot predict Y exactly because ...
1) of unknown population or sample values.
2) of other variables that also influence Y.
3) we might not know the values of X.
There are many known and unknown (or hidden) variables that also influence Y.
Consider the following hypothesis and then answer items 12 and 13:
Hypothesis: The viewing of violent video material is related to aggressive behaviour.
12. The independent variable in the hypothesis above is ...

1) viewing of violent video material.
2) aggressive behaviour.
3) There is no independent variable.
The correct option is 1.

The independent variable is that variable which affects the dependent variable; or, conversely, the
dependent variable depends on the independent variable.
13. The hypothesis above ...

1) associates values of the independent variable with values of the dependent variable.
2) implies which levels of àggressive behaviour' are caused by viewing violent video material.
3) is a theory about how violence on videos and aggressive behaviour are connected.
Option 1 is correct:
As the values of the independent variable change, the dependent variable should also change (if
the hypothesis is valid). Option 2 is incorrect because this particular hypothesis does not state
that one variable `causes' another.
14. The observation that à child hits another child' can be considered to be ...
1) an observation of a manifest variable.
2) a behavioural consequence of àggressive behaviour'
Option 3 is the correct answer.
The observation that à child hits another child' can be considered to be a behavioural
consequence or manifestation of the construct àggressive behaviour'. We infer that the
behaviour is the consequence of the construct, and the construct is made visible (manifest) by the
behaviour.
15. An hypothesis is general or universal in nature in the sense that ...

1) the postulated relation is linear.
2) the relation is proposed for a population.
3) the postulated relation will hold in a specific sample.
Hypotheses that are true only for one or more samples are of no value in building theories that
will allow us to understand and explain behaviour. Option 3 is incorrect as hypotheses are not
stated for samples.
16. A sample is ...

1) a segment of a population
2) a representation of the population
3) random
The correct option would be option 2.
To say it is à segment of a population' as option 1 claims, seems to imply that a specific subgroup
is deliberately chosen, and the whole idea is that the sample should represent the population as
well as possible. Option 3 is not true of all samples. Random samples are desirable, but are not
always possible or practical.
17. An inference is ...

1) another term for hypothesis
2) an inspired guess
3) a generalisation based on existing information
The correct option would be option 3.

something you have found has more general implications. It is not an hypothesis (as option 1
suggests), although you may use an inference to develop an hypothesis.
For example, on the basis of the popularity of TV dramas that contain high levels of violence, you
infer that people are entertained by watching violent behaviour. You can then turn this into a
hypothesis for further study. Àn inspired guess', as stated in option 2 may be a good description
of a hypothesis, but not for an inference, which is based on specific information.
18. Òperationalisation' refers to ...

1) the process of forming a hypothesis
2) the process of finding a practical way of measuring a construct
3) finding a practical operation or procedure to do the research
Here the best answer would be 2.
Òperationalisation' is where you make the construct (which is usually an abstract concept, so it is
difficult to observe it clearly) visible by finding some suitable way to measure it. You need it to
be able to test an hypothesis, but it is not in itself `the process of forming an hypothesis', as
suggested in option 1. Option 3 `finding a practical operation or procedure to do the research' is a
bit too vague, and would be more suitable as a definition of research design.
19. To say that a construct is `latent' is another way of saying it is ...

1) hidden from direct observation
2) abstract
3) a concept that forms part of a theory
The fact that constructs are usually abstractions does play a role in making them latent, but it
does not imply that àbstract' and `latent' mean the same thing, as suggested in option 2.
Option 3 is true of constructs in general, but this is not related to the fact that they are not
directly observable.
20. Parameters are ...

1) another word for descriptive statistics
2) values that indicate certain important aspects of the data obtained from a sample
3) values that summarise aspects of population data
Options 1 and 2 are false because while the word `parameters' does refer to descriptive statistics,
it does not refer to all descriptive statistics. It is used only for those descriptive statistics that
relate to the population, not to those that describe aspects of the sample.
21. In psychological research, a theory is best understood as ...

1) a list of constructs
2) an educated guess
3) an explanation of how facts are connected
Option 3 is correct (see section 1.2.2).
Option 1 is incorrect because a theory is not just a list of constructs, but an account of how
constructs are related to one another. Option 2 is incorrect because a theory is not just a guess,
but a description of how observations fit together in an explanatory framework.
22. To operationalise a construct means to ...

1) explain the construct to a lay person

2) classify the construct
3) set up criteria so that the construct can be measured
The primary aim of operationalisation is to describe a construct clearly and unambiguously so that
it can be measured and tested in a research study.
23. The main difference between constructs and variables, is that constructs are (a) ... and variables
are (b) ...
1) (a) qualitative (b) quantitative
2) (a) latent (b) manifest
3) (a) constant (b) variable
Option 1 is incorrect because variables and constants can both be qualitative or quantitative.
Option 3 is incorrect because a construct is an abstract theoretical entity and not a constant (i.e. a
numerical value that is constant).
24. A psychologist has a theory that anxiety influences the exam marks that students obtain in
statistics. In this example exam performance is ...
1) a latent variable
2) a dependent variable
3) an independent variable
In the study the psychologist proposes that ànxiety' has an effect on èxam performance'.
Ànxiety' is, therefore, the independent variable, and èxam performance' is the variable that is
actually being measured, the dependent variable. Option 1 is incorrect because exam
performance is a manifest and not a latent variable.
25. In psychological research the term `hidden variables' refers to ...

1) all the latent constructs in a theory
2) all the unknown variables that can exert an influence on the independent variables in an
experiment
3) other variables that may also affect the dependent variable, but that the researcher does
not explicitly focus on in a research study
Option 1 is incorrect because the term `hidden variables' is used to denote other variables that
could have been, but were not specifically controlled for in a research study, and does not to refer
to all the possible constructs in a theory (there would be a very large number of such constructs).
Option 2 is also incorrect, because although other variables (called covariates) could also influence
the independent variables, the term `hidden variable' specifically relates to variables that
influence the measurement of the dependent variables.
Topic 2
1. A researcher randomly selects a child from a group of 300 boys and 400 girls to participate in a
research experiment. What is the probability that the child selected will be male?
1) 0.5
2) 0.43

3) 0.57
To calculate the probability that the child will be a boy, we use our formula
Therefore, there is a 0.43 probability that the child will be a boy.
2. With reference to the question above, what is the probability that the child selected will not be a
male?
1) 0.5
2) 0.43
3) 0.57
option 3 is correct
Since we have determined that p(boy) = 0.43, we know that p(not boy) will be 1 ± 0.43 = 0.57.
There are only two possibilities (boy or not boy) so one is the other subtracted from 1.
3. A street magician shows you a deck of 52 playing cards and asks you to randomly pick a card from
the pack, without showing him what card you take. He then correctly informs that you picked an ace.
What is the probability that he could have guessed correctly simply by chance?
1) 1/52
2) 1/13
3) 1 /27
the correct option is 2
There are four aces in an ordinary deck of 52 cards. The probability of picking an ace by chance is
4. Select the statement below that provides the most accurate formulation of the law of large
numbers:
1) Any probability value will eventually converge on an average value.

2) Probability estimates are prone to considerable error because one can never predict
probabilities accurately.
3) If a statistical experiment event is performed a large number of times, a specific outcome
will tend to converge on its theoretical probability.
The correct option is 3.
Option 1 is not correct, because it omits the important condition of the law of large numbers,
namely, that the event has to be performed a large number of times before the theoretical
probability will be reached.
5. A student writes in her research report that p(Hypothesis 1: true) 4 ±0,3. Upon reading this, her
supervisor becomes angry. Why?
1) The student has given no reason for her conclusion.

2) A probability cannot be negative.

3) One should always state a confidence level when formulating a hypothesis, and the student
did not do this.
Option 2 is correct
Probability values fall in the range 0 to 1, and are always positive. Option 2 is correct because any
supervisor would be annoyed if a student used a negative probability value. A negative p-value
has no interpretation.
6. The standard normal distribution has a mean of ............... and a standard deviation of ............
1) 0; 1
2) 1; 0
3) 1; 1
Option 1 is correct
The definition of the standard normal distribution (see section 2.3.3) is that it has a mean of 0 and
a standard deviation of 1.
7. A ............... is completely described by the mean and the standard deviation.
1) normal distribution
2) population
3) sample
Option 1 is correct
Any normal curve can be generated provided that we know its mean and standard deviation.
Populations and samples are not necessarily normally distributed, so that further information may
be needed to describe them. Therefore, options 2 and 3 are incorrect.
8. A researcher at Unisa administers an attitude scale to a group of research participants. Their

average score is 2, and the standard deviation is 2. Suppose a participant obtains a score of 2, what
is her z-score?
1) 2
2) 0
3) 1
Option 2 is correct
Since the score that you obtained is exactly the same as the mean, we know that your z-score is 0,
because it does not deviate from the mean at all.
9. The first exam in a statistics course yielded a normal distribution of scores with a mean of 35 and a
standard deviation of 10. If you were to select the score of one student at random, what is the
probability that the score would be 45 or above?
1) 0.34
2) 0.66
3) 0.16
The correct option is 3
The z-score for a score of 45 is

The score, therefore, lies one standard deviation above the mean, so that 0.84 of the scores lie
below it. The probability of a score of 45 or higher is, therefore, 1 ± 0.84 = 0.16.
10. Which of the following statements about population parameters is the most accurate?
1) They are essential for making statements about probability.

2) They are usually unknown.
3) They are essential, but cannot be estimated from sample information.
option 2 is correct
Population parameters are usually unknown and have to be inferred from sample data. Since
population parameters are unknown, they cannot be essential to make statements about
probability. Option 1 is, therefore, incorrect. Option 3 is also incorrect because it incorrectly states
that population parameters cannot be estimated from sampling information, but the whole
process of statistical inference is actually concerned with inferring information about a population
from sample data.
11. The larger the sample, the more likely it is that the sample will accurately reflect the population
mean.
1) True
2) False
The statement is true, so option 1 is correct.
Larger samples will contain less individuals with only extreme values and are more likely to have a
normal distribution. Larger samples will, therefore, reflect the population mean more accurately
than small samples.
12. A researcher is interested in the IQ of students at his college. The researcher believes that the IQ
of college students, measured by means of a standardised test, has a mean of 110 and a standard
deviation of 15. The researcher takes a random sample of college students and finds that the mean
IQ is 120. Which of the following situations provides the strongest evidence that the mean IQ of his
students is greater than 110? (Note: n = size of sample.)
1) n = 10
2) n = 50
3) n = 100
Since option 3 is the largest sample, we can expect it to provide the best indication of the true
population mean.
From the previous question we know that larger samples are more likely to describe the
population mean accurately.
13. When the sample size (n) decreases, the dispersion of the sample means
1) becomes less.
2) becomes greater.
3) remains the same.

Alternative 2 is correct.
The spread or dispersion of the sampling distribution of means is given by the standard deviation
of the sampling distribution of means (i.e. the standard error). The formula for determining
this standard deviation is σ/n (see section 2.4.2), and the value becomes larger as n decreases.
Questions 14 and 15 are based on the following research scenario:
A national survey of college students indicates that students drink an average of 4.1 alcoholic
beverages per week. A researcher randomly selects 30 college students and asks each one how many
alcoholic beverages he or she consumes per week. The researcher finds that the students surveyed
drank 182 alcoholic beverages during the week.
14. What is the population mean?
1) 30
2) 4.1
3) 6.1
Our best guess about the population mean is given by the national survey, because it presumably
involved a very large sample of students. We can, therefore, assume that the population mean is
4.1 and that option 2 is correct. Option 1 is the number of students (and not the mean) and is,
therefore, incorrect. Option 3 is also incorrect because it is the mean of the small sample (n=30)
investigated by the researcher (see the calculation in the next question below), and this mean is,
therefore, less reliable as an indicator of the population mean than the data obtained from the
national survey.
15. What is the sample mean?
1) 30
2) 4.1
3) 6.1
Option 3 is correct
The sample mean is obtained by
(rounded off to one decimal place).
16. A university researcher is interested in the incomes of her psychology graduates. A national
survey shows that university graduates (from all departments) earn R127 500 on average, per year,
with a standard deviation of R30 000. The researcher believes that her college's alumni make more
than R127 000 a year (i.e. the researcher believes that the population of psychology students is
different from the population of all university students). The researcher says: Ì talked to two
graduates [a sample of 2] and they both make over R200 000 a year! Obviously, our students make
more than R127 500 per year after university.' Do you agree with this researcher? If not, indicate
why not. Cite statistical evidence in support of your answer (but no calculations are necessary).

The researcher is generalising on the basis of the two students who were questioned about their
salaries. The researcher's sample (only two students) is probably too small to make valid
inferences about the population of graduate students.
17. Why is a probability distribution always of a theoretical nature?

A relative frequency can only be used as a probability distribution if we assume that probability
theory applies. Probability theory is a theoretical approach that makes use of theoretical
constructs such as probability distributions to describe empirical phenomena.
18. Suppose we randomly draw a sample of five scores from a population and calculate the mean for
this sample. The same procedure is repeated 10 times.
1. Why are the mean values for the samples not the same?
Each sample provides a different estimate of the population because of random sampling error.
2 Given the 10 samples plus the fact that the mean of the population distribution is unknown, what
would the best estimate of the population mean be?
The best estimate of the population mean can be obtained by calculating the mean of the 10
means. NB: The 10 means can now be considered in the same way as any set of 10 scores, and we
might be interested in the mean, standard deviation, frequency distribution, et cetera, of this set
of scores.
19. Does random sampling ensure a sample that is representative of the population?
No, it does not, because of sampling error that will play a role even if random sampling is used.
However, since sampling is random, it does make it possible for one to derive a probability
distribution for a particular sample statistic, such as the sample mean. Given an hypothesised
value for the population mean, we can judge the likelihood of our sample mean under the derived
probability distribution of means.
20. Suppose that the population distribution of a dependent variable is assumed to be normal, with
a mean of 50 and a standard deviation of 10. Suppose, further, that samples of the same size are
drawn randomly from the population with replacement.
n (50; 10)
n (50; 16)
n (60; 10)
1. What would the mean of the sample means approach as the number of samples of the same size
that are drawn approaches infinity?
It will approach the numerical value of the population mean.
2 Can the frequency distribution of all the samples be fully specified?

There could be an infinitely large number of samples, each with its own mean and standard
deviation.

Yes, provided that the population mean is specified (hypothesised) and the distribution of sample
means can be assumed to be normal. The latter assumption may be made if it can be assumed
that the population has a normal distribution, or if a very large sample is selected from the
population.
21. How would you derive a probability distribution for the mean?
Assume that the theoretical distribution of sample means of the same size, selected randomly
from the population, is normal with a mean that is equal to the population mean, and a standard
deviation equal to σ/√𝑛 (if σ is known). The distribution can now be transformed to the standard
normal distribution if s is known. (Note: If s is not known, we shall have to use another
distribution, as you will see in Topic 3 (i.e., the t-distribution).)
22. Suppose a researcher transforms each score in a non-normal population to a z-score. Will these
scores be normally distributed? Are the z-scores in the z-tables normally distributed?
No. The z-transformation does not change the shape of the original distribution. The z-scores in
the z-tables are normally distributed because the z-table specifies, by definition, the standard
normal distribution.
23. Make a freehand drawing of each of the following normal distributions on the same scale:
1. a normal distribution with mean = 50, variance = 100

24. Why is the central limit theorem important?

It often happens that we doubt the assumption that the population distribution is normal.
However, the central limit theorem states that, for a large sample size, the sampling distribution
of a mean is close to normal, irrespective of the shape of the population distribution of the
original data. This enables us to make inferences about means and develop test statistics for
means.
25. Suppose a population distribution is normal with µ = 50 and σ = 15.

1. What is the raw z-score for a raw score of 70 in the population?
2. Suppose the size of the population is 10 000. How many scores greater than 70 are there in the
population?
p(z > 70) = 0.092 (from z-table in Appendix D, using the smaller portion as indicated in the graph
above.) So, we can estimate that 0.092 x 10 000 = 920 scores in the population should be greater
than 70.
3. Suppose a single case is selected from this population using a random selection process. What is
the probability that the score will be greater than 70? What is the difference between `case' and
`score'?
As we have already calculated for 2, p(x > 70) =0.92 A `case' is the particular entity being
observed, whereas a `score' is a numerical value reflecting some characteristic of the case being
considered.
4. What is the probability that a single case selected randomly will have a score between 45 and 55?

These two values are therefore an even distance away from the mean (of z=0) on the standard
normal distribution. We can, therefore, look up p(x > 45) = p(z > ±.33) which is 0.6293, and
subtract from it p(x > 55) = p(z > 33) which is 0.3707 (the larger portion and the smaller portion
respectively for z = 0.33 on the standard normal distribution tables in Appendix D). This gives p(45
5 x 5 55) = 0.6293 ± 0.3707 & 0.26.
5. Suppose 25 cases are randomly selected from the population and the mean for this sample is 45.
Is it possible to obtain a sample mean of 45 when one assumes that the population mean is equal to
50? Is it possible for the researcher to derive a theoretical distribution of the mean without selecting
even a single sample?
Yes, any result is possibly due to sampling error. However, some results (sample means) in this
example will be less probable than others. It is possible to derive a theoretical distribution for the
mean provided one knows the population standard deviation and hypothesises a value for the
mean of the population.
Topic 3
Example 1
Suppose we believe that viewing violence causes one to become more violent. Suppose a test to
measure a person's violent behaviour is standardised on a very large student sample considered to be
representative of the general student population. The test requires a student to induce an electric
shock in a monkey. Students are led to believe that they can adjust the severity of the shock by
adjusting the voltage between 0 and 600 on a dial, but do not know that only a very mild constant
shock is possible. The severity of shock selected by each student is recorded. The mean for this
standardisation group is found to be 300 and the standard deviation 50.
Question 1: Suppose that we plan to subject a single, random sample of students to the viewing of
violent material and then subject each student to the test described above to measure his or her
violent behaviour. State a research or operational hypothesis.

Answer: A population of students (call this population A) that could potentially be subjected to
the viewing of violent material will show more violent behaviour, as measured by the severity of
the shock they are prepared to give to the monkey, compared with students who are not
subjected to such violent material (call this population B).
Comments: Note that these populations (A and B) as such do not actually exist! We cannot in
practice subject all students to the viewing of violent behaviour. But we state the hypothesis in
this way to emphasise that the research hypothesis is about some relation between the viewing of
violent behaviour and the subsequent tendency towards violent behaviour in a population of
students and not in some sample. Of course, we will study a random sample of students, but this
is to find out about the relation between the two variables in the population.
Also note that this hypothesis implies
• the constructs between which a relation is being postulated, namely, `viewing of violence'
and `violent behaviour`
• the nature or rule of the relation (i.e. the more the viewing of violence, the more the
likelihood of violent behaviour)
• the research population, namely, students
• how constructs are being measured (`Severity of shock' measures constitute the
dependent variable.)
Question 2: State the null and alternative statistical hypotheses and set the value of α to 0.05.
Answer:
H0: µ = 300
H1: µ > 300
Comments: Here µ is the mean `severity of shock administered' score of a population of students
that could potentially be subjected to the viewing of violent material, and 300 is the mean of the
population that is not subjected to the viewing of violent material. The value of α is set to 0.05.
Question 3: Suppose we assume that the standard deviation of both these populations is 50 and that
the mean of population B is known to be 300. We select a single sample of 100 students randomly
and have them view a 5-minute segment of film taken from a movie that shows a man being beaten
by a group of gangsters. Thereafter, these students are subjected to the `test' of violent behaviour.
The mean score is calculated and found to be 312. The standard deviation is also calculated and
found to be 30.
Does the value of 312 appear large? Is there a logical chance that H1 might be true? Is there anything
else about this sample result that should be of concern?
Answer: The sample mean of 312 is larger than 300. This is what we would expect under H1. So,
there is a chance that the sample result of 312 might be more likely under H1 than H0. The
difference is only 12 (312 - 300 = 12), and we are in some doubt whether this is an important
difference. We assumed that the population standard deviation is 50, but we find that the
sample standard deviation is 30. Is the assumption that the population variance is 50 incorrect?
Comments: It is sometimes difficult to judge the `practical importance' of a sample result and
methods have been developed to assist the researcher in this regard. However, these methods fall
outside the scope of the present module. As far as the population standard deviation is
concerned, we can perform a statistical test on the hypothesis `σ = 50', but this test also falls
outside the scope of this module.

Question 4: Perform a statistical test procedure on the sample result. Give reasons for your choice of
the test statistic.
Answer: The appropriate test statistic is the zx test of a single sample mean, because of the
following considerations:
• The null hypothesis is about a population mean (µ); the appropriate sample result is,
therefore, a sample mean (x).
• The population distributions are assumed to be normal in shape with a known standard
deviation (σ = 50).
Comments: The z-test statistic is calculated as follows:
From the z-tables in Appendix D, the p-value (for the area above z = 2.4) is 0,0082. This is smaller
than 0,05; therefore, reject H0 and accept H1.
Question 5: What is the conclusion regarding the research hypothesis?
Answer: From a statistical point of view, the research hypothesis is confirmed. In other words, the
viewing of violent material results in increased violent behaviour among students.
Example 2
Study the AIDS evaluation scenario in Appendix A. Suppose that, after studying various research
applications of the Àttitude to AIDS' questionnaire, the trainers are satisfied that the general
population of employees in South Africa has a mean of 20.0 and a standard deviation of 3.5. The
trainers are interested in whether the large company from which their sample of 40 was selected has
a more negative attitude to AIDS than the general population of workers in South Africa.
Question 1: State the research hypothesis.
Answer: The company's workers have a more negative attitude to AIDS (as measured by the AIDS
attitude questionnaire) than the general population of workers in South Africa.
Comments: The research population is clearly èmployees in South Africa'. Note, however, that
the two populations associated with the two levels of the independent variable so that the
statistical hypotheses may be tested are as follows:
• employees of the specific company (call this population A) that requested the research,
and
• employees in all companies in South Africa (population B).
These two populations represent a way of thinking by the statistician in order to test the statistical
hypotheses, and must not be confused with the researcher's research population.
Question 2: State the null and alternative statistical hypotheses and set the value of a = 0.01.
Answer: H0: µ = 20
H1: µ > 20
Here m is the mean Àttitude to AIDS' score of all employees in the company, and the mean
Àttitude to AIDS' score for all employees in South Africa is assumed to be 20. The significance
level (α) is set to 0.01.

Comments: Note here that we accept that the Àttitude to AIDS' scores constitute interval-scale
measurements. Parameters and their corresponding statistics, such as the mean and standard
deviation, are thus appropriate summary values of the distributions involved.
Question 3: Suppose we assume that the standard deviation of the AIDS questionnaire is 3.5 for both
statistical population distributions involved and that these distributions are normal in shape. We
consider the 40 subjects in Appendix A of this module as a random sample from the company. Go to
Appendix A and let your eye roam over the 40 Àttitude to AIDS' scores. Can you compute the mean
of these 40 scores? We calculated the mean and found it to be 18.55. The standard deviation was
also calculated and found to be 3.47 (see Appendix C for the appropriate formulas). The results are
summarised in the following table:
Does the value 18.55 appear to be notably smaller than 20? Is there a logical chance that H1 might
be true? Does the sample standard deviation of 3.47 look likely given the assumption that the
population standard deviation is 3.5?
Answer: The number 18.55 is smaller than 20, as we would expect under H1. There is thus a
chance that H1 might explain the results better than does H0. The difference does not look
noteworthy, as a difference of 20 - 1.55 = 1.45 on a scale that ranges from 11 to 25 does not look
like an important difference. The sample standard deviation of 3.47 does look close to the
assumed population standard deviation of 3.5.
Question 4: Perform a statistical test procedure on the sample result. Use a significance level of α =
0.01. Give reasons for your choice of the test statistic.
Answer: The appropriate test statistic is the zx of a single sample mean, because of the following
considerations:
• The null hypothesis is about a population `mean`; the appropriate sample result is,
therefore, a sample `mean'
• The population distributions are assumed to be normal in shape with a known standard
deviation, namely, 3.5.
From the z-tables in Appendix D, the p-value for the area under the curve, left of z = -2.64 is
0.0041. This is smaller than 0.01: therefore, reject H0 and accept H1.
Question 5: What is the conclusion regarding the research hypothesis?
Answer: As the alternative hypothesis is accepted, and this hypothesis corresponds closely to the
research hypothesis, we may consider the research hypothesis to be confirmed or verified. It does

appear that the employees of this company are more negative to AIDS than the general employee
in South Africa.
Study the passage below and then answer questions 1 to 8.
A psychologist hypothesises that sleep deprivation affects cognitive performance negatively. He

selects a sample of 16 students randomly and deprives them of sleep for 10 hours over and above the
normal 14 hours during which they are awake in a day. He then measures each student's
performance on a computer game, which requires cognitive skill to perform. It is also known that the
general population of students has a mean score of 1 200 for this particular computer game, with a
standard deviation of 200. Suppose it is found that the mean score for the sample is 1 050 and that
the level of significance is set at 0.05.
Question 1.1: What is the null hypothesis?
1) The mean score of all students in the computer game is 1 200.

2) The mean score of all students deprived of sleep in the computer game is 1 200.
3) The mean score of 16 students in the computer game is 1 200.
Note that option 1 refers to the population of students not deprived of sleep and merely states
what we know of this population. Option 3 is clearly incorrect as hypotheses are never about
samples.
Question 1.2: What is the alternative hypothesis?
1) The mean score of all students in the computer game is less than 1 200.
2) The mean score of all students deprived of sleep in the computer game is less than 1 200.
3) The mean score of all students in the computer game is greater than 1 200.
The correct answer is option 2
The researcher expects sleep deprivation to affect cognitive performance negatively.
Option 1 is incorrect because we already know that the population of students in general has a
mean of 1 200 and we do not test this. We are testing, however, whether a population of sleep-
deprived students would score lower than 1 200. Option 3 is also incorrect as it does not refer to a
population of sleep-deprived students.
Question 1.3: Several assumptions about the population of scores have to be made so that the
sampling distribution of the mean may be derived. Which one of the following assumptions is not
made?
1) The shape or form of the distribution is normal.

2) The sampling process is random.
3) The population of scores is known.
This assumption may be true as far as all those students not deprived of sleep are concerned, but
is not true as far as the population of students deprived of sleep is concerned. Option 1 is
incorrect since we do actually assume that populations are normally distributed. Option 2 is also
incorrect, because we do assume that samples are randomly selected, because then it becomes
possible to derive the sampling distributions of sample statistics.

Question 1.4: If a is set at 0.05, which of following statements is true?
1) The probability of a Type I error will not exceed 0.05.

2) The p-value of the study cannot exceed 0.05.
3) Both of the above.
The p-value associated with the actual result of the study might be smaller than 0.05, thus
indicating a probability of a Type I error smaller than 0.05 but not larger. The actual p-value of the
result can of course be any size between 0 and 1. Option 2 is, therefore, incorrect and, therefore,
also option 3.
Question 1.5: The mean value of the sampling distribution of the mean is
1) 1 200.
2) 1 050.
3) Unknown under H0.
We derive the mean value of the sampling distribution of the mean under the null hypothesis, and
because we know that µẋ = µ, which is 1 200 under the null hypothesis.
Question 1.6: What is the value of the standard error?
1) 50
2) 200
3) 12.5
The standard error is the standard deviation of the sampling distribution of the mean. From
section 2.4.2 we know the formula is
Question 1.7: The value of the zx -statistic is
1) ±0.59.
2) 3.0.
3) ±3.0.
Question 1.8: What can you conclude about the hypothesis (stated in 1.1 and 1.2 above), using the
value of zx calculated in the previous question and testing at the significance level of α = 0.05?
1) The null hypothesis cannot be rejected. Sleep deprivation does not affect cognitive
performance in a negative way.

2) The null hypothesis should be rejected. Sleep deprivation does not have an effect on
cognitive performance.
3) The null hypothesis can be rejected. The results show that sleep deprivation has a negative
effect on cognitive performance.
Look up the p-value for zẋ = -3.0 in die z-tables in Appendix D. You should find that p(z > 3.0) =
0.0013, which is the appropriate p-value for this test. Keep in mind that since the distribution is
symmetrical, the `smaller portion' at the far left (for a negative z-score) will be equivalent to
the area at the far right (for a positive score). This p-value is smaller than the level of significance
of α = 0.05, and it implies that the null hypothesis can be rejected in favour of the alternative
hypothesis. In other words, sleep deprivation has a significant negative effect on cognitive
performance. Option 1 is false and in option 2 the wrong conclusion is made after the null
hypothesis is rejected.
Exercise 2: Study the passage below and then answer questions 1 to 8.
A researcher has developed a measurement of àttitude to capital punishment' among adults such
that the higher a score on the test, the more a person expresses himself in favour of capital
punishment or displays a positive attitude to capital punishment. The researcher standardised the
test on a large sample of men, and, after several different studies, concluded that the general level of
attitude to capital punishment of the general population of men can be assumed to be normal with a
mean (µ) of 30 and a standard deviation of 11. Forty adult men were then selected randomly and
shown a video in which hanging for murder was shown in detail. The test was then administered to
the sample and the following results were found: ẋ = 29 and s² = 100.
Question 2.1: The research hypothesis states that
1) the sample becomes more negative in its attitude.

2) exposure to capital punishment influences attitudes negatively.
3) exposure to capital punishment influences attitudes.
Option 3 provides the clearest expression of the research hypothesis.
Option 1 is obviously incorrect because a hypothesis is never about samples. Option 2 is incorrect
because there is no explicit indication in the problem scenario that the researcher expects that
attitudes will become more negative (even though a person reading the scenario may expect
that this is what would happen). We have no option but to state a research hypothesis with an
alternative hypothesis that is nondirectional.
Question 2.2: The alternative statistical hypothesis is
1) H1: µ > 30.

2) H1: µ < 30.
3) H1: µ ≠30.
Option 3 is correct
The alternative hypothesis has to be non-directional.
Question 2.3: The mean of the sampling distribution of the mean is
1) 29.
2) 30.

3) unknown.
Option 2 is correct
we know that µẋ= µ and that µ = 30 under the null hypothesis. Option 1 is incorrect because it
refers to a sample result and not a population mean.
Question 2.4: The standard deviation of the sampling distribution of the mean is
1) 100.
2) 10.
3) 1.74.
Question 2.5: The value of zẋ is
1) -0.57.
2) -0.45.
3) -0.1.
Question 2.6: Suppose the value of zẋ is found to be 1.5. What is the p-value?
1) 0.0668
2) -0.0668
3) 0.1336
The one-tailed p-value is 0.0668 (from Appendix D), but because we have a non-directional
alternative hypothesis, the two-tailed p-value is 2 x 0.0668 = 0.1336. Note that option 2 is
obviously incorrect since a probability cannot be negative!
Question 2.7: Suppose the appropriate p-value was found to be 0.07 and the level of significance is
0.10. What should the decisions be regarding the statistical hypotheses?
1) Reject the null hypothesis and accept the alternative hypothesis.

2) Do not reject the null hypothesis.
3) Accept the null hypothesis, but reject the alternative hypothesis.
Note that option 3 is obviously incorrect as the null hypothesis is never accepted. The decision
regarding the null hypothesis is to reject it or not to reject it.

Question 2.8: Suppose the appropriate p-value was found to be 0.07 and the null hypothesis was
rejected because of this p-value. Has a Type I error been committed?
1) No.
2) Yes.
3) It is not possible to say.
Because we can never know what the true situation is in the population, we do not know, and will
never know, if the decision to reject the null hypothesis has been an error. We can, however,
calculate the probability that a Type I error has been made. This is given by the p-value.
Topic 4
Multiple-choice questions and solutions
1. A researcher hypothesises that a population mean for the variable àggression' is significantly
different from some known specific value. She draws a sample from an identified population of
subjects and computes the sample mean so that she can use the tx statistic to test her hypothesis.
What type of comparison is implied in this procedure?
1) Comparison of sample means.

2) Single sample with s known.
3) Single sample with s unknown.
Correct answer: Option 3.
Only one sample was drawn from a single population of subjects, to be compared with a mean
that was known (so we do not need a second sample) and with s unknown. If we knew the
population standard deviation (σ), we could use a zẋ test.
2. For what reason would we calculate the tx test statistic? It is used to determine whether a ...
1) population parameter such as a mean differs significantly from a given value

2) relationship exists between a population parameter and a sample parameter.
3) sample mean is distributed randomly.
Option 2 is wrong because the sample parameter is used to estimate the population parameter,
but this is not what is compared in the test. Option 3 is wrong because, although a random
sample is a precondition for doing the test, this is not what is being tested.
3. Consider the following from the case study presented in Appendix A: The mean pre-knowledge
score for workshop participants was 6.05, and the standard deviation 1.79. Use this to estimate the
standard error (which is the standard deviation of the sampling distribution of the mean).
1) 0.400
2) 0.283
3) Not enough information.
The standard deviation of the sampling distribution of the mean is estimated by using the
following equation:

where n is the size of your sample and s is the standard deviation of the sample (the formula is
explained in Topic 4.2.1). In this case, the sample size is 20 because 20 participants attended the
workshop.
Therefore:
4. Referring to the AIDS evaluation scenario (Appendix A), suppose that the mean population pre-
knowledge score concerning HIV/AIDS is 5.8. Which is the correct t-statistic for the data in question
3?
1) 0.1396
2) -0.625
3) 0.625
The t-statistic is calculated using the following
formula:
that is, the mean pre-knowledge score for the sample minus the mean pre-knowledge score for
the sampling distribution of the mean, divided by the standard deviation of the sampling
distribution of the mean that you calculated in question 3.
5. Consider the following from the case study (Appendix A): The mean post-knowledge score for
workshop participants was 10.65 and the standard deviation 3.199. What is the standard deviation
for the sampling distribution of the mean?
1) 0.506
2) 0.715
3) 0.159
The standard deviation of the sample distribution of the mean can be estimated by using the
following equation:
where n is the size of your sample and s is the standard deviation of the sample. In this case the
sample size is 20 because 20 participants attended the workshop. Therefore:

6. Referring to the case study regarding AIDS (Appendix A), suppose that the mean population post-
knowledge score concerning HIV/AIDS is 9.4. Which is the correct t-statistic for the data in question
5?
1) 1.748
2) -1.748
3) 0.391
The t-statistic is calculated using the following formula:
That is, the mean post-knowledge score for the sample minus the mean post-knowledge score for
the sampling distribution of the mean divided by the standard error that you calculated in
question 5. If you subtracted the mean post-knowledge score for the sample from the mean post-
knowledge score of the population, you would have arrived at answer 2.
7. Assume that we are testing the following hypothesis: Individuals who attend workshops on
HIV/AIDS have a higher level of knowledge about the disease than the population at large. Suppose
we know the knowledge level score for the general population (from previously compiled norms),
and we find a t-statistic of 1.71, which leads to a p-value of 0.0518. Which interpretation is correct?
Assume α = 0.05
1) Cannot reject the null hypothesis on a 5% level of significance. Individuals who attend
workshops on HIV/AIDS do not have different levels of knowledge about the disease when
compared to the general population.
2) Reject the null hypothesis in favour of the alternative hypothesis on a 5% level of
significance. Individuals who attend workshops on HIV/AIDS have a higher level of
knowledge about the disease than the general population.
3) Not enough information is given to decide whether or not the null hypothesis should be
rejected for any given level of significance.
Correct answer: Option 1 is correct.
The application of the decision rule should read:
Because 0.0518 is not equal to or less than the chosen significance level of 0.0500, do not reject
the null hypothesis in favour of the alternative hypothesis.
8. When the results of a t-test were entered into a computer program to calculate the p-value, a one
tailed result of p = 0.042 was returned for a test of an alternative hypothesis that states H1: µ1 = µ2.

What can we conclude if we choose a significance level of α = 0.05?
1) Reject the null hypothesis in favour of the alternative hypothesis.

2) Do not reject the null hypothesis.
3) Reject the alternative hypothesis in favour of the null hypothesis.
We cannot reject the null hypothesis. Remember that when you receive a one-sided p-value for a
two-sided test, the p-value should be multiplied by two. Now 2 x 0.042 = 0.084, which is larger
than our chosen level of significance of α = 0.05.
Topic 5
Study the AIDS evaluation scenario in Appendix A with regard to the variable, àttitude to AIDS'.
Assume that the two groups (treatment and control) were equal with regard to their attitude scores
before training commenced. State a research hypothesis implying that the training was successful in
improving attitudes, then state the statistical hypotheses. Now answer questions 1 to 18 below.
1. The research hypothesis implies that
1) the two samples are dependent.

2) the dependent variable affects the independent variable.
3) the treatment group will score higher than the control group on the dependent variable.
Option (3) is correct.
Option (1) is incorrect because the treatment and control groups are independent. Option (2) is
incorrect as the independent variable affects the dependent variable and not the other way
around.
2. The research population is
1) all employees in South Africa.

2) all employees in the company.
3) undefinable.
The issue is whether training is effective or not and not whether the company is different from
other employers in South Africa.
3. The samples are
1) randomly selected.
2) randomly assigned to experimental and control groups.
Note that in the case of true experimental designs, random assignment to groups is always
possible, whether random sampling from the general population took place or not. Therefore,
random assignment to groups does not imply that random selection took place in the first place.
The researcher sometimes uses a non-random sample and then divides the sample randomly into
an experimental and a control group. This latter process is known as random assignment to
groups.

4. Measurements on the àttitude to AIDS' test can be viewed as a/an
1) nominal scale.
2) interval scale.
3) ordinal scale.
See Appendix B.
5. If the alternative hypothesis is µ1 < µ2, then µ1 is
1) the sample mean of the post-attitude scores of group 1.

2) the population mean of post-attitude scores from which group 1 was selected.
3) the unknown parameter under the null hypothesis.
Option (1) is incorrect because hypotheses are never about sample statistics but about population
parameters. Option (3) is too vague to be correct.
6. The appropriate test statistic is
1) tc
2) zc
3) td
Option (1) is correct
we are comparing two independent samples with regard to their means.
7. The assumptions underlying the t-test are
1) equal distributions and normal variances.

2) unknown standard deviations.
3) normal population distributions with equal variances.
8. Consider the following statistics regarding the post-training àttitude' scores:
What are the values in the table called?
1) Population parameters
2) Sample statistics
3) Test statistics

Option (2) is correct

These values refer to calculations based on a sample of data (see section 1.4.3).
9. Based on the data in question 8, what is the value of the t-test statistic?
1) -2.3
2) -2.3
3) +1.3
The tC value is calculated as follows:
10. Suppose the two-tailed p-value for the t-test of the differences between the two means in
question 8 is 0.19. If a is set to 0.10, what is the decision regarding H0?
1) Do not reject H0 because 0.19 > 0.10.

2) Accept H1 because 0.19 > 0,1.
3) Reject H0 because 0.095 < 0.10.
The correct option is (3).
Because the alternative hypothesis is directional, implying that group 1 will score higher than
group 2, which is indeed the case, we apply a directional test. This requires that we divide 0.19 by
2, which gives 0.095. As 0.095 is less than 0.10 (the significance level), the null hypothesis should
be rejected and the alternative hypothesis accepted.
11. The p-value gives
1) the probability that the difference between 21.65 and 20.40 could be significant.
2) the probability that the difference between 21.65 and 20.40 could be due to chance.
3) the probability that the difference between 21.65 and 20.40 could be true.
The p-value always reflects the probability that the result is due to chance.
12. Suppose you are convinced that you cannot make the assumption that the two groups are equal
with regard to pre-training àttitude to AIDS'. How would you establish if the training was successful
in improving àttitudes to AIDS'?
1) Perform statistical tests on pre-training attitude scores.

2) Perform statistical tests on the difference between pre- and post- training attitude scores.
3) Perform a t-test for dependent groups.
We have to compare the two groups with regard to their mean `difference' score. The idea is to
show that group 1 became more positive in attitude relative to group 2.
13. Suppose one feels uncomfortable with the assumption that population distributions are normal.
It is helpful if
1) sample sizes are large.

2) sample standard deviations are known.
3) (a) and (b).
The larger the sample sizes, the more the sampling distribution will tend to be normal,
irrespective of the shape of the population distribution (see Topic 2 on the central limit theorem).
Option (2) is incorrect. Sample standard deviations are always known, as we can always calculate
them.
14. Suppose we want to determine if the control group in the AIDS study (Appendix A) improved as
far as its attitude scores are concerned. One should
1) compare pre- and post-training scores on the àttitude' variable for the control group.
2) compare the control group with the experimental group on attitude scores.
3) perform a t-test on the post-training scores.
15. If three groups are being compared with regard to their mean scores, one
1) should consider an analysis of variance strategy.

2) should join two of the groups and proceed with a t-test.
3) could do either of the above.
16. When the differences between two sample means look large, one
1) will find the result to be statistically significant.

2) may still find that the result is not statistically significant.
3) should reject the null hypothesis in favour of the alternative hypothesis.
Given that a particular result is in the right direction (favouring H1), it is necessary to perform a
statistical test to see whether the result is significant. A large effect can fail to be significant if the
sample is too small. The smaller the sample, the greater the probability of finding a result that
appears to be significant purely by chance. This relates to issues like the power of the test and
effect size (see sections 3.3.2 and 3.3.3).
17. Suppose one finds an impressive difference between two sample means, but the result is found
to be statistically insignificant. One may

1) repeat the study with larger samples.

2) decrease the α level.
3) recalculate the p-value, but for a larger α level.
Option (1) is the only one of the three options that makes sense.
18. Suppose the t-statistic is found to be -1.2. This indicates
1) a non-significant result.
2) a significant result if, on the basis of H1, we expect a negative t-value.
3) a significant result if the appropriate p-value is smaller than α.
You have to know what the p-value is that is to be compared with the level of significance, α.
Topic 6
1. Two of the following are correlation coefficients. Which one is not valid?
1) -0,02
2) 1.0
3) 1.1
The answer is (3).
A correlation coefficient can never be larger than 1.
2. Which best describes the purpose of calculating a correlation coefficient?
To determine
1) the strength of the linear relationship between two variables.

2) whether a relationship exists between two variables.
3) whether the relationship between two variables is positive or negative.
Option (1) provides a good description of what a correlation coefficient is used for.
3. A correlation coefficient can vary
1) from 1 to 10.
2) from ±1 to 1.
3) from 0 to 1.
The correct answer is (2).
4. If you get a Pearson correlation of 0 between two variables, you may conclude that
1) there is no correlation at all.

2) there is no linear correlation.
3) as it is impossible to get a correlation of 0, a calculation error was made.

Two variables exhibiting a correlation coefficient of close to zero may actually show a good non-
linear correlation.
5. What do you call a variable that can take on only one of two possible values?
1) dichotomous
2) biserial
3) binary
6. Another name for the Pearson's r is
1) Spearman's rho.
2) product-moment correlation.
3) Pearson's chi square.
7. The Pearson's r is likely to be used to establish a relationship between two variables when
1) both variables are measurements on a nominal or categorical scale.

2) continuous variables are correlated with nominal variables.
3) both variables are continuous measurements.
Correlation cannot be used for nominal scale measurements, except in the case of dichotomies
(i.e. only two categories).
8. The correlation between the two variables, Predictability and Locus-of-Control, is given as r = -
0.2861. This means that
1) as the value of Predictability becomes smaller, so does the value of Locus-of-Control.

2) as the value of Predictability becomes smaller, the value for Locus-of-Control becomes
larger.
3) as the value of Locus-of-Control becomes larger, so does the value for Predictability.
A negative correlation implies that, as one variable gets larger, the other diminishes.
9. A correlation coefficient of r = 0.3531 was found between Duration and Control. If the original
data are to be plotted on a scatter plot, it will be found that
1) the dots in the scatter plot cannot be approximated to a straight line.

2) the dots will approximate to a straight line from bottom left to top right.
3) the dots will approximate to a straight line from top left to bottom right.
This is a positive correlation, so, as one variable gets larger, so does the other.
10. If duration were to be correlated with itself, the result would be

1) r = 1.
2) r = 0.
3) r cannot be calculated, for a variable cannot be correlated with itself.
A variable correlated with itself will form a perfect correlation, since the variables being compared
are perfect matches.
11. The Pearson r represents the relationship between
1) the observed and the expected frequencies of the data.

2) the covariance of two variables and the product of the variance of each.
3) the variance of one variable and the variance of the other.
Option (1) refers to the chi-square test.
12. Suppose the alpha-value was set to α = 0.05. A chi-square test statistic of ‫א‬² = 3.5 is calculated,
and it is found that the matching p-value is 0.04.
Which of the following statements is true?
1) The null hypothesis can be rejected since 0.05 is less than 3.5.
2) The null hypothesis cannot be rejected since 0.05 is not less than 0.04.
3) The null hypothesis should be rejected since 0.04 is less than 0.05.
The general rule in hypothesis testing is to see if the calculated p-value is equal to or less than the
predefined level of significance (α), in which case the null hypothesis can be rejected.
13. When you want to establish whether a relationship exists between two nominal-level or
categorical variables, the best test to use is
1) the Pearson r.
2) the t-test.
3) the chi-square test.
The Pearson correlation coefficient cannot be used for nominal scale measurements (except when
both measurements are dichotomies, in which case more appropriate tests than Pearson's r exist),
nor can the t-test be used in such a case.
14. What is the expected frequency (given the null hypothesis) for the top left cell in the following
contingency table used to calculate the chi-square statistic?

1) 5
2) 2
3) 8
Multiply the column total for group A with the row total for type 1, and divide by the overall total:
15. The chi-square test statistic ‫א‬²p is used to compare
1) the observed frequency distribution and the expected frequency distribution.

2) the covariance of two variables and the variance of each.
3) the variance of a variable and its frequency distribution.
The second option (2) refers to the Pearson's r and option (3) makes no sense at all.
16. Which of the following values of Pearson's r represents the strongest relationship between two
variables?
1) r = 0.058
2) r = 0.44
3) r = -0.70
The fact that the correlation is negative indicates that, as one variable gets larger, the other gets
smaller, but the absolute value of the correlation coefficient (ignoring the sign) shows how strong
the correlation is.

Powered by TCPDF (www.tcpdf.org)

Pyc3704 Question and Answer or Memo

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Pyc3704 Question and Answer or Memo

Uploaded by

Copyright:

Available Formats

PYC3704 Psychological Research

Exam Questions and Answers

The study-notes marketplace

Downloaded by: maestrofusa | maestrofusa@gmail.com

1 PYC3704 Psychological Research

This document is a compilation of UNISA Exam Questions and Answers

Answers are motivated by a combination of:

• Short summaries/reasoning regarding the relevant topic(s) in question. (Incorrect options

Exams covered are:

• 2017 October November

• Test yourself Questions and Answers from the Study Guide

Downloaded by: maestrofusa | maestrofusa@gmail.com

2 PYC3704 Psychological Research

May June 2016

A theory can be described as an interdependent set of - - - - - relations between - - - - -

Answer: The correct option is 1

A measurement model of attention deficit disorder relates this - - - - - to its - - - - -

1. construct, intervening variables

Answer: The correct option is 2

Use the following scenario to answer Questions 3 to 5

Downloaded by: maestrofusa | maestrofusa@gmail.com

3 PYC3704 Psychological Research

Answer: The correct option is 2

The dependent variable(s) in my research is/are - - - - -

1. personality factors, nature of stressors, support received

Answer: The correct option is 3

Answer: The correct option is 1

Downloaded by: maestrofusa | maestrofusa@gmail.com

4 PYC3704 Psychological Research

Answer: The correct option is 2

Use the following scenario to answer Questions 7 and 8

The statement "estimated size increases with haziness" represents the - - - - -

1. observed relation between two variables

Answer: The correct option is 2

The dependent variable(s) in Jeff's research is/are - - - --

Answer: The correct option is 3

Downloaded by: maestrofusa | maestrofusa@gmail.com

5 PYC3704 Psychological Research

Answer: The correct option is 3

1. Education is relevant to the promotion of employees at Computer Solutions Inc

Answer: The correct option is 3

Downloaded by: maestrofusa | maestrofusa@gmail.com

6 PYC3704 Psychological Research

A standard normal distribution has a standard deviation of - - - - - and a mean of - - - --

Answer: The correct option is 2

Consider the hypothesis:

1. As repetitions of a probability experiment increases, the relative frequency or proportion of

Answer: The correct option is 1

Downloaded by: maestrofusa | maestrofusa@gmail.com

7 PYC3704 Psychological Research

Answer: The correct option is 3

During the interpretation of psychological measurements, the normal distribution is often - - - - -

1. adapted to fit the observed frequency distribution of scores

Answer: The correct option is 2

Relative to the rest of his class Joseph does - - - - -

1. better in History that in Biology

Answer: The correct option is 1

Downloaded by: maestrofusa | maestrofusa@gmail.com

8 PYC3704 Psychological Research

1. frequency, age in months

Answer: The correct option is 2

Base your answers to Questions 18 and 19 on the following scenario

A researcher is investigating job satisfaction of workers at a branch office of a particular company.