Statistical test revision for quiz - ANS

Correlation test

1 Chickens produce eggs.

The effect of the age of a chicken on the mass of the eggs it laid was investigated.
A statistical test can be used to see if there is a significant correlation between the
age of a chicken and the mass of her eggs.
The value generated by this statistical test will always be between −1.0 to +1.0.
The table shows the mass of eggs collected from chickens of different ages.
Age / Rank of Mass of egg Rank of D D2
weeks age /g mass of egg

36 1 2.27 8 −7 49
1 1 1
39 2 1.91

42 3 2.18 5.5 −2.5 6.25

45 4 2.28 9 −5 25

48 5 2.12 4 1 1

51 6 2.19 7 −1 1

54 7 2.18 5.5 1.5 2.25

57 8 2.09 3 5 25
7 49
60 9 2.03 2

(i) Calculate the value for ΣD2.

Use the table to help you.
(2)
2
• correct D values (1)
• correct calculation of ∑D2 (1) ∑D2= 159.5
Correct answer with no working shown scores full marks
1 mark awarded for correct ∑ using incorrect D2 values calculated in table
ΣD2 = ..............................................................
(ii) Calculate the correlation coefficient, rs value, for this data using the formula:
(2)

• correct values substituted into formula (1) 957 ÷ 720

• correct rs value (1) -0.329 / -0.33 / -0.3
Allow ECF from answer calculated in (c)(i)
Correct answer with no working shown scores full marks
Answer ..............................................................

(iii) The null hypothesis is that there was no significant correlation between the age
of the chicken and the mass of the eggs laid.
Another scientist replicated this study and gained a correlation coefficient value of
0.38.
The table shows the critical values at the 95% probability level.

Critical values at the 0.05

Number of pairs of data % probability level

8 0.738

9 0.683

10 0.648

Explain whether the null hypothesis should be accepted or rejected.

(2)
An explanation that includes the following points:
mark points independently
• (the null hypothesis) should be accepted (1)
• (because) 0.38 is lower than 0.683 (1)
2 The relationship between the length and swimming speed of the sperm cells of 30
cichlid species was investigated.
The graph shows the results of this investigation.

(i) State the relationship between the mean length and swimming speed of the
sperm cells of these cichlid species.
(1)
An answer that includes the following point:
• as (sperm) length increases the (sperm swimming) speed increases /
positive correlation between (sperm) length and (sperm swimming)
speed (1)
IGNORE {linear / positive / proportional} relationship

(ii) A scientist wanted to assess the strength of the relationship between these two
variables.
Which statistical test should be used to assess the strength of the relationship
between these two variables?
(1)
 A chi‑squared test
 B correlation coefficient
 C index of diversity
 D Student’s t‑test
3 The diagram shows three different zones found in a plant root.

(a) Cells in zone 1 carry out interphase, mitosis and cytokinesis.

A student stated the hypothesis that:
In zone 1, the percentage of cells carrying out mitosis decreases from the tip to the
start of zone 2.

(i) State the null hypothesis for this investigation.

(1)
there is no change in the percentage of cells carrying out mitosis from the
tip to the start of zone 2/ there is no correlation between percentage of
cells carrying out mitosis from the tip to the start of zone 2.

(ii) Describe how could the significance of the results be determined once the
percentage of cells in mitosis is determined in each of these zones.
(2)
1. use of a named appropriate statistical test (1) e.g. Spearman’s rank
correlation, or (Student’s) T test (to compare two different regions)
2. comparison of calculated value to critical value (to accept or reject the
student’s hypothesis) (1)
4 A student planned to keep two species of fish in an aquarium.
One species of fish should be kept at a minimum temperature of 25 °C. The other
species requires a minimum concentration of oxygen of 7.5 mg dm−3 water.
(a) The student investigated the effect of water temperature on the solubility of
oxygen in water.
The table shows the results of this investigation.

The student used a statistical test on these data.

(i) Which is the correct statistical test to use on these data?
(1)
 A Chi squared test
 B correlation coefficient
 C standard deviation
 D Student’s t test
(ii) The student analysed the data using the formula:

The student calculated d2 to be 108.

Use the formula to calculate rs.
(3)

1. calculated (1) 6 × 108 = 648

2
2. n(n -1) calculated (1) 7(49-1) =336
3. correct rs value given (1) 1 - (648 ÷ 336) = -0.93 / 0.93 / -0.929 / 0.929

ACCEPT ecf from and n(n2-1) calculations

Answer ..............................................................

(iii) Explain how the student should use the rs value calculated in (a)(ii) to find the
strength of the relationship between these two variables.
(2)
An explanation that makes reference to the following:
1. critical value found at {p = 0.05 / 95% level confidence level / 5%
significance level} (1) ACCEPT 0.01 / 99 %
2. because if {calculated / rs} value is greater than critical value there is a
{strong / significant} {relationship / correlation} (1) ACCEPT converse
t-test

1 Fruit drinks are a good source of vitamin C.

A student investigated the concentration of vitamin C in three different fruit drinks.
The table shows the results for these fruit drinks.

Explain how the student could determine whether the difference between the
concentrations of vitamin C in the three fruit drinks was significant.
(3)
An explanation that makes reference to three of the following:
1. several measurements for each fruit drink (1)
2. statistical test carried out (1) e.g. student t-test
3. calculated value compared to the critical value (1)
4. at the {5% significance level / p=0.05} (1)

2 Emphysema is a condition that causes changes to the tissues in the lungs.

In an investigation, the surface area for gas exchange and the volume of the lungs of
three groups of individuals were determined. The results are shown in the table.

There appears to be a difference in the lung volume of individuals with mild

emphysema and those with severe emphysema.

Which of the following would be a relevant statistical test to determine whether this
difference is significant?
(1)
 A chi‑squared
 B correlation coefficient
 C standard deviation
 D Student’s t‑test
3 A student investigated the effect of salt concentration on the growth of one
species of brine shrimp.
The student placed 100 shrimp eggs in a beaker containing 1dm3 of 3% salt solution.
Three days after the eggs hatched, 10 shrimps were collected and their lengths
measured. Seven days after hatching, another 10 shrimps were collected and their
lengths measured.
The procedure was repeated using a 5% salt solution. All other variables were kept
constant.
The results are shown in the table.

(a) Calculate the mean length of shrimp three days after hatching in the 5% salt
solution. Give your answer to an appropriate number of significant figures.
(1)
correct answer to four significant figures (1)
Example of calculation
6.44 ÷ 10 = 0.644 (mm)
Answer .............................................................................. mm
(b) The student carried out a statistical test to see if there was a significant difference
between the mean lengths of brine shrimps in these two salt solutions. The student
used the 7 days after hatching data.
The student selected the t-test because the data are normally distributed.
(i) Complete the table by filling in the missing value for specimen 7 and then
calculate the value for Σx12
(1)

specimen 7 = 1.277
AND
Σx12 = 12.198
(ii) The variances are used in the calculation of a t-value.
The variance for the 3% salt solution S12 = 0.0059.
Calculate the variance for the 5% salt solution (S22 ) using the formula

n = the number of specimens (2)

1. Top line of formula correctly calculated (1)

2. correct answer to two significance figures (1)
Example of calculation
9.055 – 9.006 = 0.0054 / 0.00544 / 5.4 x 10-3
S22 .............................................................................................

(iii) Calculate the t-value using the formula.

Give your answer to an appropriate number of significant figures.

(3)
1. top line of formula correctly calculated (1)
2. bottom line of formula correctly calculated (1)
3. correct answer to between three and five significant figures (1)
Example of calculation
t=0.153
0.0336 (0R 0.0337 if 0.00544 used)
= 4.55 (OR 4.54 if 0.00544 used)
ALLOW answer between 4.5510 and 4.5540
t = .............................................................................................

(iv) The calculated t-value is greater than the critical value at p = 0.05.
Describe what this result indicates about the effect of salt concentration on the
length of brine shrimp.
(2)
An explanation that makes reference to the following:
1. there was a significant difference between {the 3% and the 5% salt
solution / groups} (1) IGNORE significant correlation / significant
relationship
2. at the 5% significance level (1) ALLOW 95% probability there is a
difference
e.g. ‘5% chance that the difference is due to chance’ or with 95%
certainty’ IGNORE p = 0.05
4 Soil pH is one of the abiotic factors that affects the population size of earthworms.
The populations of earthworms in the fields with either acidic soil or alkaline soil
have been investigated.
The results of this investigation are summarised in the table.

Explain how differences between the mass of earthworms in these two soils could be
shown to be statistically significant.
(3)
A description that makes reference to three of the following:
1. find mean values (1) ALLOW use of mean values
2. use a t-test/ calculate a t-value (1) IGNORE chi-squared test
3. (calculated) t-value needs to be greater than the critical value (1) ALLOW
compare the t-value to the critical value
4. (compared to cv for) probability of { 0.05 / 5% } (1)
Chi-squared test

1 The drawing shows a speckled chicken. These chickens have a mixture of black and
white feathers.
The colour of the feathers of a chicken is an example of codominance.
One parent of this speckled chicken had white feathers and the other
parent had black feathers.

In an experiment, several pairs of speckled chickens were mated together.

They produced 480 chicks.
The table shows the expected number of speckled chicks, white chicks and black
chicks. It also shows the actual number of each type of chick.

Steps in the Colour of feathers of chicks

calculation for the
Speckled White Black
statistics test

Observed number (O) 243 125 112

Expected number (E) 240 120 120

-8
(O-E) 3 5 ACCEPT 8
DO NOT ACCEPT -3/-5
2 0.5333
(O-E) 0.0375 0.2083 64/120
E 9/240 25/120 8/15
3/80 5/24
ACCEPT 2 or 3 or 4 dps
but not necessarily
consistently the same
This table can be used in a statistics test. number.
(i) Name the statistics test being used to analyse these data.
DO NOT ACCEPT
(1)
Chi squared (1) recurring
ACCEPT Chi square / X squared / x squared / X2 / x2 / chi2 distribution (test) /
chi (test) / closeness of fit / goodness of fit

(ii) Complete this table to show the missing values.

(2)
All correct = 2 marks
One row correct = 1 mark
(iii) Calculate
(1)

0.8 / 0.78 / 0.779 / 0.7791 (1) CE / rounding effect from (c)(ii)

DO NOT ACCEPT 0
NB 187/240 = 0.7792
Answer ..............................................................

(iv) Explain how a critical value table could be used to accept or reject a null
hypothesis for this experiment.
(2)
An explanation that includes two of the following points:
• {calculate / use} the number of degrees of freedom (1)
ACCEPT description of how to work out degrees of freedom
• use (a probability) value of (up to or equal to) 5%/0.05 (1)
• compare (calculated) {value / result} to (critical) value (1)
• if the (calculated) {value / result} is greater than (critical) value then null
hypothesis is rejected (1) NB mp 4 alone = 2 marks
ACCEPT the converse argument
ACCEPT any quoted figures for the calculated value
2 In a study of inheritance, fruit flies with different traits were crossed.

The table shows the phenotypes and numbers of fruit flies produced in the F2
generation.

A chi squared test was performed with an expected ratio of 1:1:1:1 for the four
phenotypes. The calculated value from the test was 10.64.

The table shows critical values for chi squared distribution.

Analyse the data to determine whether the F2 offspring numbers differ significantly
from a 1:1:1:1 ratio of phenotypes.
(3)
An answer that makes reference to the following points:
1. there are three degrees of freedom in the data (1)
2. the critical value at p < 0.05 is 7.81 (1)
3. since 10.64 is greater than 7.81 there is a significance difference from
expected (1)
3 Lettuce plants usually grow upright. This is the ‘upright’ phenotype.
In one variety of lettuce the stem of the lettuce grows along the ground. This is the
‘weary’ phenotype.
These two phenotypes are shown in the diagram.

(a) Inheritance of the weary phenotype has been investigated.

Scientists crossed weary lettuce plants with upright lettuce plants.
The F1 generation produced from this cross were all upright.
In the second cross, two of the F1 lettuce plants were crossed with each other to
produce the F2 generation.
The phenotypes of the F2 generation and the results of a statistical test are shown in
the table.

Justify the conclusion that the weary phenotype was inherited as a recessive trait.
(3)
An answer the makes reference to three of the following:
1. no offspring from the cross between weary and upright lettuce had the
weary phenotype (1) ALLOW none of the F1 generation had the weary
phenotype / all the F1 generation were upright
2. the ratio of weary to upright lettuce in the F2 generation was 1: 3 (1)
ALLOW {25% / ¼ / 27.7%} of the F2 generation were weary lettuce
3. the chi-squared test value was below the critical value (1)
ALLOW less than a critical value of 3.84
IGNORE degrees of freedom or incorrect cv
4. result not statistically different from expected result (1)
ALLOW the null hypothesis can be accepted