ERS5950 EDUCATIONAL STATISTIC

FINAL EXAM QUESTIONS

(SET A)

DR SHAMSULARIFFIN SAMSUDIN

Part 1:

1. The covariance is:

[A] A measure of the strength of relationship between two variables.

[B] Dependent on the units of measurement of the variables.
[C] An unstandardized version of the correlation coefficient.
[D] All of these.

2. R2 is known as the:

[A] Coefficient of determination.

[B] Multiple correlation coefficient.
[C] Partial correlation coefficient.
[D] Semi-partial correlation coefficient.

3. What is b0 in regression analysis?

[A] The value of the outcome when all of the predictors are 0.
[B] The relationship between a predictor and the outcome variable.
[C] The value of the predictor variable when the outcome is zero.
[D] The gradient of the regression line.

4. Levene's test tests whether:

[A] Data are normally distributed.

[B] The variances in different groups are equal.
[C] The assumption of sphericity has been met.
[D] Group means differ.

5. A researcher was interested in stress levels of lecturers during lectures. She took
the same group of 8 lecturers and measured their anxiety (out of 15) during a
normal lecture and again in a lecture in which she had paid students to be
disruptive and misbehave. What test is best used to compare the mean level of
anxiety in the two lectures?

[A] Independent samples t-test

[B] Paired-samples t-test
[C] One-way independent ANOVA
[D] Mann–Whitney test
6. The t-test tests for:

[A] Differences between means

[B] Whether a correlation is significant
[C] Whether a regression coefficient is equal to zero
[D] All of these

7. A researcher measured people’s physiological reactions to horror films. He split

the data into two groups: males and females. The resulting data were normally
distributed and men and women had equal variances. What test should be used
to analyse the data?

[A] Dependent
[B] Independent t-test
[C] Mann–Whitney test
[D] Wilcoxon signed-rank test

8. What assumption does ANCOVA have that ANOVA does not?

[A] Homogeneity of variance

[B] Homoscedasticity
[C] Homogeneity of sample size
[D] Homogeneity of regression slopes

9. A music teacher had noticed that some students went to pieces during exams. He
wanted to test whether this performance anxiety was different for people playing
different instruments. He took groups of guitarists, drummers and pianists (variable
= ‘Instru’) and measured their anxiety (variable = ‘Anxiety’) during the exam. He
also noted the type of exam they were performing (in the UK, musical instrument
exams are known as ‘grades’ and range from 1 to 8). He wanted to see whether
the type of instrument played affected performance anxiety while accounting for
the grade of the exam. What analysis should he use?

[A] Independent analysis of variance

[B] Repeated measures analysis of variance
[C] Analysis of covariance
[D] Mixed analysis of variance

10. ANCOVA is:

[A] Used to correct for unmeasured variables that could affect the outcome
variable.
[B] Is a method of portioning the results of ANOVAs to investigate where
differences between independent variables
[C] Is a robust version of ANOVA.
[D] An extension of ANOVA that partials out the effect of other measured variables.

11. If you are comparing two (or more) different groups, what is this design called?
 [A] Between participants.
[B] Unrelated.
[C] Independent.
[D] All of the above.

12. The t test can be defined as:

[A] a ratio between a measure of between-groups variance and within-groups

variance.
[B] a ratio between a measure of between-groups standard deviations and within-
groups means.
[C] a ratio between the two confidence intervals.
[D] a measure of between-groups variance and within-groups variance.

13. To which of the examples below could you apply the use of a t-test?
[A] You are looking to see if reaction time is significantly correlated with alcohol
consumption.
[B] You are looking to see if depression and social support are related.
[C] You are testing whether there is a significant difference in intelligence
between rugby players and footballers.
[D] All of the above.
14. Which of the following statements is true of the value of t in an independent t-test?
[A] The larger the variance is between groups compared with the variance within
the groups, the smaller the t-value is.
[B] The smaller the variance is between groups compared with the variance
within the groups, the larger the t-value is.
[C] The smaller the variance is between groups compared with a larger variance
within the groups, the larger the t-value is.
[D] The larger the variance is between groups compared with the variance within
the groups, the larger the t-value is.
15. A correlation coefficient of +0.40 could be considered:

[A] strong.
[B] weak.
[C] moderate.
[D] zero

16. A researcher is examining the relationship between depression and adult

attachment. However, he has reason to believe that childhood attachment
influences both of these. He decides to calculate some partial correlations. Which
of the following, if any, should he do?
 [A] Examine the relationship between depression and adult attachment controlling
for childhood attachment.
[B] Examine the relationship between depression and childhood attachment
controlling for adult attachment.
[C] Examine the relationship between childhood attachment and adult attachment
controlling for depression.
[D] None of the above are possible.

17. The correlation coefficient (r) is a ratio between the covariance (variance shared
by two variables) and a measure of the separate variances.
True /false

18. For a positive relationship ____ scores on one variable tend to be associated with
____ scores on the other variable
[A] high; high
[B] low; high
[C] high ; low
[D] none of the above

19. We can plot relationships on a graph called a histogram.

[A] True
[B] False

20. What conclusions can you draw from bivariate correlational analyses?
[A] The direction of the relationship.
[A] The strength of the relationship between two variables.
[B] Both of the above answers.
[C] Causation only.

21 What could we say about these results?

Number of offences Age

Pearson's correlation 1.000 .89
Number of Sig. (2 tail) . .000
offences N 40 40

Age Pearson's correlation .89 1.000

Sig. (2 tail) .000 .
N 40 40

[A] These results tell us that the relationship between number of offences
committed and age was found to be positively and moderately related (r =
+.89, p < 0.0001, n = 80). Thus as number of offences rises, so does the age
of offender.
[B] These results tell us that there is a perfect relationship between number of
offences committed and age (r = +.1.00, p = 0.000, n = 40). Thus as number
of offences rises, so does the age of offender.
[C] These results tell us that the relationship between number of offences
committed and age was found to be positively and strongly related (r =
+.89, p < 0.001, n = 40). Thus as age of offender rises, so do the the number
of offences.
[D] These results tell us that the relationship between number of offences
committed and age was found to be positively and strongly related (r =
0.001, p < 0.89, n = 20). Thus as number of offences rises, so does the age
of offender.

21. What relationship is the strongest from this set of data?

 Motivation Exam Depression
marks scores
Motivation Pearson's 1.000 .8801 -.0110
correlation
Sig. (2 tail) . .000 .811
N 400 400 400
Exam Pearson's .8801 1.000 -.1459
marks correlation

Sig. (2 tail) .000 . .001

N 400 400 400
Depression Pearson's -0.110 -.1459 1.000
scores correlation
Sig. (2 tail) .811 .001 .
N 400 400 400

[A] Motivation and exam marks.

[B] Depression and exam marks.
[C] Motivation and depression.
[D] None are strong associations.
22. When two variables are correlated we can say:
[A] high scores are frequent on x and y.
[B] that they are independent.
[C] that they have a perfect positive relationship.
[D] that they share variance.

23. Which of the following tells us that we have a perfect positive relationship?
[A] r = +1
[B] All the points on the scatterplot would fall on a straight line and the slope
would be from bottom left to top right of the plot.
[C] The dots would fall in a straight line from top left-hand corner down to
bottom right hand corner.
[D] Both the first and second answer.

24. Which of the following is incorrect?

 [A] r is a natural effect size.
[B] r can be squared to give a measure of variance explained.
[C] If two variables are correlated then they are not dependent. As scores on one
variable changes, scores on another variable changes in an unpredictable
way.
[D] In a correlation matrix each variable correlates perfectly with itself

25. When conducting an ANCOVA in SPSS, which function would you select from the
‘analyse’ drop down list?

[A] ANCOVA.
[B] Time Series.
[C] Classify.
[D] General Linear Model.

26. Which of the below assumptions must be met in order to conduct ANCOVA?

[A] The regression lines for the different groups must be parallel to each other.
[B] The covariate should be linearly related to the dependent variable.
[C] The covariate should be measured without error (reliable).
[D] All of the above.

27. A researcher wants to test the differences between three treatment conditions
(cognitive-behavioural therapy, aversion therapy and behavioural therapy) by
assigning individuals randomly to one of the three conditions. The researcher
would need to perform which of the following tests to analyse the results?

[A] Repeated measures ANOVA.

[B] One-way between groups ANOVA.
[C] Fisher's Exact Probability Test.
[D] Pearson's r.

28. ANOVA tells us that there is a difference due to our IV(s) and where these
differences lie.
[A] true
[B] false

29. What does the ‘group’ row refer to?

Source Type III Sum of df Mean square F Sig.
squares
Group 68.222 2 34.111 .000
Error 19.334 6 3.222
Total 87.556 8 10.945
[A] Group row refers to the within-groups statistics and is the row of interest.
[B] Group row refers to the descriptive statistics and is the row of interest.
[C] Group row refers to the level of significance statistics and is the row of interest.
[D] Group row refers to the between-groups statistics and is the row of interest.

30. When interpreting a correlation coefficient, it is important to look at:

[A] The +/– sign of the correlation coefficient.

[B] The magnitude of the correlation coefficient.
[C] The significance of the correlation coefficient.
[D] All of these.

31. The correlation between two variables A and B is .12 with a significance of p <
.01. What can we conclude?

[A] That there is a substantial relationship between A and B.

[B] That variable A causes variable B.
[C] That there is a small relationship between A and B.
[D] All of these.

32 A researcher was interested in stress levels of lecturers during lecturers. She took
the same group of 8 lecturers and measured their anxiety (out of 15) during a normal
lecture and again in a lecture in which she had paid students to be disruptive and
misbehave. Based on the SPSS output, how would you interpret these results?

[A] There were no significant differences between anxiety levels in normal lectures
and in those in which students misbehaved.
[B] Anxiety levels were significantly higher in lectures in which students misbehaved.
[C] We can’t tell any of the above from the output given.
[D] Anxiety levels were significantly lower in lectures in which students misbehaved.

33. A psychologist was interested in whether there was a gender difference in the
use of email. She hypothesized that because women are generally better
communicators than men, they would spend longer using email than their male
counterparts. To test this hypothesis, the researcher sat by the email computers in her
research methods laboratory and when someone started using email, she noted
whether they were male or female and then timed how long they spent using email (in
minutes). What should she report?

[A] Females and males did not significantly differ in the time spent using
email, t(7.18) = –1.90, p = .10.
 [B] Females and males did not significantly differ in the time spent using
email, t(14) = –1.90, p = .10.
[C] Females and males did not significantly differ in the time spent using
email, t(7.18) = –1.90, p < .05, one-tailed.
[D] Females spent significantly longer using email than males, t(14) = –1.90, p <
.05.

34. A researcher was interested in the effects of emotion-evoking music on exam

performance. Before their SPSS exam, a lecturer took one group of students to a room
in which calming music was being played. A different group of students were taken to
another room in which the ‘death march’ was being played. The students then did the
exam and their marks were noted. The SPSS output is below. The experimenter made
no predictions about which form of support would produce the best exam performance.
What should he report?

[A] Students receiving positive music before the exam did significantly better than
those receiving negative music, t(38) = 2.05, p = .047.
[B] Marks for students receiving positive music before the exam did not
significantly differ from students receiving negative music, t(38) = 2.05, p =
.047.
[C] Marks for students receiving positive music before the exam did not
significantly differ from students receiving negative music, t(23.12) = 2.05, p =
.052.
[D] Students receiving positive music before the exam did significantly better than
those receiving negative music, t(23.12) = 2.05, p < .05, one-tailed.

35. An independent t-test is used to test for:

 [A] Differences between means of groups containing the same entities when the
sampling distribution is not normally distributed and the data do not have
unequal variances.
[B] Differences between means of groups containing the same entities when the
data are normally distributed, have equal variances and data are at least
interval.
[C] Differences between means of groups containing different entities when the
data are not normally distributed or have unequal variances.
[D] Differences between means of groups containing different entities when the
sampling distribution is normal, the groups have equal variances and data are
at least interval.

36. A researcher measured a group of people’s physiological reactions while

watching horror films and compared them to when watching comedy films. The
resulting data were normally distributed. What test should be used to analyse the data?

[A] Wilcoxon signed-rank test.

[B] Mann–Whitney test.
[C] Paired-samples (dependent or related) t-test.
[D] Independent t-test.

37. All of the following techniques are commonly used in exploratory research
EXCEPT

[A] In-depth interviews with key informant survey.

[B] Examination of purchase behaviour through observation.
[C] Experiments.
[D] Qualitative research through focus groups.

38. H0 : Intentions to buy computers via the Internet do not depend on nationality
Ha : Intentions to buy computers via the Internet do depend on nationality
Assume that ‘intentions to buy computers via the Internet’ has been measured using
a 5-point Likert interval scale, which of the following tests is appropriate?
[A] Independent samples t-test.
[B] One sample t-test.
[C] Simple regression analysis of intentions to buy computers via the Internet on
nationality.
[D] Chi-square test for goodness-of-fit.

39. Assume that researchers want to find out whether the satisfaction with life is
dependent on gender for which they created the following hypotheses:
H0 : Women are equally or less satisfied with life than men.
Ha : Women are more satisfied with life than men.
Respondents had to answer the following questionnaire question: how satisfied are
you with the life you are currently living? They could answer on a scale from 1 (very
dissatisfied) to 7 (very satisfied).

Looking at the output above, what would you conclude if you coded 1 = male and 2 =
female (at a significance level of 5%)?
[A] One cannot reject H 0 because the observed level of significance is 0.061.
[B] One can reject H 0 because the observed level of significance is 0.0295.
[C] One can reject H 0 because the observed level of significance is 0.0305.
[D] One cannot reject H 0 because the observed level of significance is 0.059.

40. Hassan tests the following set of hypotheses with an independent samples t-test:

H0 : Students that spend more than 15 minutes in the first round of registration give the
same or a higher evaluation for the current course scheduling procedure than students
that spend 15 minutes or less.

Ha : Students that spend more than 15 minutes in the first round of registration give a
lower evaluation for the current course scheduling procedure than students that spend
15 minutes or less.

She gets the following output:

Which of the following statements is true?

 [A] One cannot assume equal variances because the p-value of the Levene’s Test
for Equality of Variances is .786.
[B] One cannot assume equal variances because the p-value of the Levene’s Test
for Equality of Variances is .393.
[C] One can assume equal variances because the p-value of the Levene’s Test for
Equality of Variances is .786.
[D] One can assume equal variances because the p-value of the Levene’s Test for
Equality of Variances is .393.

Part 2

Question 1 (30 marks)

A quasi-experiment was conducted to identify the Problem Based Learning Strategy

(PBL) effectiveness towards students’ mathematics performance. This study
compares the PBL strategy group (treatment group) and conventional group (control
group). Before the actual experiment starts, a pre-test give to students from both
groups. After eight weeks, a post-test was conducted on the students from both
groups.
a. Based on the research, state the research objectives with two null hypotheses
(Ho). [4 Marks]
b. State the appropriate analysis that has been conducted. [1Mark]
 c. Based on Table 3 and 4, write the full report (including tables) based on APA
format to explain and discuss the findings [9 Marks]

Table 3
Mean N Std. Deviation Std. Error Mean
Pre-test 47.22 32 21.248 3.756
Pair 1
Post-test 59.06 32 18.770 3.318
* PBL strategy group
Table 4
Paired Differences t df sig
Mean Std. Std. 95%
Deviati Error Confidence
on Mean Interval of the
Difference
Lower Upper
Pre-test – - 18.036 3.188 - -5.341 - 31 .001
Pair 1
Post-test 11.844 18.346 3.715
PBL strategy group

The researchers also want to investigate the PBL strategy approach compared to the
post-test score's conventional system. The findings for the analysis are as in table 5
and 6
1. What is the appropriate analysis for the test? [1 Mark]
2. Based on Tables 5 and 6, write a report of the APA format findings, including
the tables. [12 marks]
3. Discuss the findings by suggesting what action needs to be taken by the
researchers. [3 Marks]

Table 5
Class N Mean Std. Std. Error
Deviation Mean
PBL strategy group 32 59.06 18.770 3.318
POST_Test
Conventional group 30 36.00 16.887 3.083

Table 6
Levene's t-test for Equality of Means
Test for
Equality of
Variances
F Sig. t df Sig. (2- Mean Std. Error 95% Confidence
tailed) Differenc Differenc Interval of the
e e Difference
Lower Upper
POST Equal .511 .477 5.074 60 .000 23.063 4.545 13.971 32.154
_ variances
Test assumed
 Equal 5.092 59.904 .000 23.063 4.529 14.002 32.123
variances
not assumed

Question 2 (35 Markah)

A study was conducted to determine the relationship between parental support, school
environment, student’s motivation towards mathematics, and teacher support with
school students’ mathematics engagement in Selangor. For the study, the following
hypothesis has been created

Ho1: there is no significant relationship between parental support with students’

mathematics engagement
Ho2: there is no significant relationship between school environment with students’
mathematics engagement
Ho3: there is no significant relationship between student’s motivation towards
mathematics with students’ mathematics engagement
Ho4: there is no significant relationship between teachers support with students’
mathematics engagement

By referring to Diagram 1, write a report to answer all the research hypotheses using
APA format. Discuss also the findings

Diagram 1: Correlation between variables studied

[15 Marks]

The study also investigates factors that might influence student’s mathematics
engagement in the state of Selangor. A multiple regression using ENTER method was
conducted, and the analysis was as shown in Diagrams 2, 3, and 4. Create the report
based on the analysis and discuss the findings.
The discussion should include the actions needed to help increase students'
mathematics engagement in the future.

Diagram 2: Model Summary

Diagram 3: ANOVA

Diagram 4 : Coefisien Table