m

2018

3) 57 63 1 6
(i) G 1 .
1 . 38 1 .
48 1 . 56 1 .
.

3 6 8 9 101

B 1 27. 1 .
28
1 32
. 1 35
.
1 .

44 5

12457
is o
difference
Ho :
population median

H: difference is larger then

population median

1 + 2+ 4 + 5+ 7 =
19

5x(5 + 6 + 1) -

19 =
4)

19717
accept Ho

insufficient

(ii) x 18 x (20+ 18 + 1) =

35/
# x 18 X 20 x (2018 + 1) =
1170

-23
430 6
561x
= .

x -

35)* 79 -

.
Non-parametric tests

past paper questions

122 NON-PARAMETRIC TESTS

1 [9231/s22/41/q6] 12

6 A teacher at a large college gave a mathematical puzzle to all the students. The median time taken by a
random sample of 24 students to complete the puzzle was 18.0 minutes. The students were then given
practice in solving puzzles. Two weeks later, the students were given another mathematical puzzle of
the same type as the first. The times, in minutes, taken by the random sample of 24 students to complete
this puzzle are as follows.

18.2 17.5 16.4 15.1 20.5 26.5 19.2 23.2

17.9 18.8 25.8 19.9 17.7 16.2 17.3 16.6
17.1 20.1 20.3 12.6 16.0 21.4 22.7 18.4

The teacher claims that the practice has not made any difference to the average time taken to complete
a puzzle of this type.
2-tailed
Carry out a Wilcoxon signed-rank test, at the 10% significance level, to test whether there is sufficient
evidence to reject the teacher’s claim. [10]

0 2.
-
0 .

5 -66-29 2 5 8 5
.
.
1 2
.
52
....................................................................................................................................................................
:

0. 0 8 7 8 1 9 0 31 8 0 7 +. 4
....................................................................................................................................................................
-
-
-
. . .

. .
.

09 201 23 5.4 20 3 4 4 10 4
....................................................................................................................................................................
-
- - . .
.

....................................................................................................................................................................
5 11 + 81724921
....................................................................................................................................................................
2 -
-

I 7 23 13 =3 12-6 To
....................................................................................................................................................................
- -

8 1516 22-1419204
....................................................................................................................................................................
-
-

....................................................................................................................................................................
Ho population median is 18 0
....................................................................................................................................................................
:
.

H : population median is not 18 0

....................................................................................................................................................................
.

....................................................................................................................................................................

#x24x25 150
....................................................................................................................................................................
=

2x24x25x49 1225
....................................................................................................................................................................
=

....................................................................................................................................................................
110 5-150
1 1293
.

1 645
....................................................................................................................................................................
= -

d1225
- .

....................................................................................................................................................................

accept Ho
....................................................................................................................................................................

insufficient evidence to
suggest that population
....................................................................................................................................................................

median is not 18 0
....................................................................................................................................................................
.

© UCLES 2022 9231/41/M/J/22

CHAPTER 4. NON-PARAMETRIC TESTS 123

2 [9231/s22/43/q5] 8

5 A manager claims that the lengths of the rubber tubes that his company produces have a median of
5.50 cm. The lengths, in cm, of a random sample of 11 tubes produced by this company are as follows.

5.56 5.45 5.47 5.58 5.54 5.52 5.60 5.35 5.59 5.51 5.62
-
+ + + + -
+ + +
+
-

0 .
06 =

0 .
05 -

0030 . 08 0 .
04 p . 02010 -
0 .

15 0090 01 .
0: 2

It is required to test at the 10% significance level the null hypothesis that the population median length
is 5.50 cm against the alternative hypothesis that the population median length is not equal to 5.50 cm.

Show that both a sign test and a Wilcoxon signed-rank test give the same conclusion and state this
conclusion. [9]

0 ....................................................................................................................................................................
+
-

+-
+ ++ -
+ + +

P(x =3) = "Cox05" + "Cixa5" + "CeX05" "CxQ5"

....................................................................................................................................................................
+ = 0 113 .

....................................................................................................................................................................
0 .
11370 05 .

0 05 003 0 08 0 04 0 02010 0 15 01 Dir

0090
....................................................................................................................................................................
② 0 06
-
.
.
=
-
. . .

5
-

37429-18110
....................................................................................................................................................................
6
....................................................................................................................................................................
19447 Hoi median is 5 50
.

....................................................................................................................................................................
median is not 5 50
H
: .

19713
....................................................................................................................................................................

accept Ho
....................................................................................................................................................................
median is not 5 50
.

insufficient evidence support

to
....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

© UCLES 2022 9231/43/M/J/22

124 CHAPTER 4. NON-PARAMETRIC TESTS

3 [9231/w22/41/q3] 6

3 A large college is holding a piano competition. Each student has played a particular piece of music and
two judges have each awarded a mark out of 80. The marks awarded to a random sample of 14 students
are shown in the following table.

Student A B C D E F G H I J K L M N
Judge 1 79 54 63 74 69 52 50 57 55 42 63 55 56 48
Judge 2 75 62 60 73 76 41 31 51 45 55 49 50 65 36
4 -

831 -

7119610 +

13145-912
(a) One of the students claims that on average Judge 1 is awarding higher marks than Judge 2. Carry
out a Wilcoxon matched-pairs signed-rank test at the 5% significance level to test whether the data
supports the student’s claim. [7]
(b) Give a reason why it is preferable to use a Wilcoxon matched-pairs signed-rank test in this situation
rather than a paired sample t-test. [1]

(a)4 -

831 -

7119610 +

13145-912

3
-

21
-

6101459 + 2134-811
............................................................................................................................................................
median difference is O
33272 Ho :
population
............................................................................................................................................................

population median difference is

............................................................................................................................................................
H1
larger
:

33725
than 0
............................................................................................................................................................

accept Ho
............................................................................................................................................................
support population
median
insufficient evidence to
............................................................................................................................................................
difference is larger than 0
............................................................................................................................................................

(b)............................................................................................................................................................
unknown
population
............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................
© UCLES 2022 9231/41/O/N/22
CHAPTER 4. NON-PARAMETRIC TESTS 125

4 [9231/w22/42/q6] 10

6 The manager of a technology company A claims that his employees earn more per year than the
employees at technology company B. The amounts earned per year, in hundreds of dollars, by a random
sample of 12 employees from company A and an independent random sample of 12 employees from
company B are shown below.

Company A 461 482 374 512 415 452 502 427 398 545 612 359
Company B 454 506 491 384 361 443 401 472 414 342 355 437

(a) Carry out a Wilcoxon rank-sum test at the 5% significance level to test whether the manager’s
claim is supported by the data. [9]

(b) Explain whether a paired sample t-test would be appropriate to test the manager’s claim if earnings
are normally distributed. [1]
(a)

A 61 545 4824445398so
B5064914724544434374144 % 384361355342
17 15 B 1298642
2) 19

Ho median difference is
:
population
is not o
H 1:
population median difference
............................................................................................................................................................

2x12x25 150
............................................................................................................................................................
=

............................................................................................................................................................
+ 2
X 12x12x25 300 =

............................................................................................................................................................
127 5 150
299
-

+1
.

= .

............................................................................................................................................................
↓ 300
............................................................................................................................................................
-

1 2997
. 1 645-

............................................................................................................................................................

............................................................................................................................................................
accept Ho
median
to support that population
............................................................................................................................................................
insufficient evidence

difference is not o
............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................
© UCLES 2022 9231/42/O/N/22
126 CHAPTER 4. NON-PARAMETRIC TESTS

5 [9231/s21/41/q5] 10

5 Georgio has designed two new uniforms X and Y for the employees of an airline company. A random
sample of 11 employees are each asked to assess each of the two uniforms for practicality and
appearance, and to give a total score out of 100. The scores are given in the table.

Employee A B C D E F G H I J K
Uniform X 82 74 42 59 60 73 94 98 62 36 50
Uniform Y 78 75 63 56 67 82 99 90 72 48 61
4 + -

2)3 -

7 =

9 -

58 -

10 -
12 +

1
(a) Give a reason why a Wilcoxon signed-rank test may be more appropriate than a t-test for
investigating whether there is any evidence of a preference for one of the uniforms. [1]

(b) Carry out a Wilcoxon matched-pairs signed-rank test at the 10% significance level. [7]

cal unknown
population
(b) Ho unknown difference is
population
:

Hi unknown difference is not

population
:

4 + -

2)3 -

7 =

9 -

58 -

10 -
12 +

11713

rejectHo
unknown difference
sufficient evidence to support population
is O
not

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................
© UCLES 2021 9231/41/M/J/21
CHAPTER 4. NON-PARAMETRIC TESTS 127

6 [9231/s21/43/q2] 3

2 A company is developing a new flavour of chocolate by varying the quantities of the ingredients.
A random selection of 9 flavours of chocolate are judged by two tasters who each give marks out of 100
to each flavour of chocolate.

Chocolate A B C D E F G H I
Taster 1 72 86 75 92 98 79 87 60 62
Taster 2 84 72 74 95 85 87 82 75 68
12
14-
-

3438-5156
Carry out a Wilcoxon matched-pairs signed-rank test at the 10% significance level to investigate
whether, on average, there is a difference between marks awarded by the two tasters. [7]
Ho difference is 0
:
population
....................................................................................................................................................................
median

Hi : population difference is
....................................................................................................................................................................
median not O

12 14 - 3438-5156
....................................................................................................................................................................
-

6 -

8 -2 -

>T 3 94
....................................................................................................................................................................
5
-

1978
....................................................................................................................................................................

accept Ho
....................................................................................................................................................................

insufficient evidence to support that population

....................................................................................................................................................................
median

difference is
....................................................................................................................................................................
not o

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................
© UCLES 2021 9231/43/M/J/21 [Turn over
128 CHAPTER 4. NON-PARAMETRIC TESTS

7 [9231/w21/41/q6] 12

6 The blood cholesterol levels, measured in suitable units, of a random sample of 11 women and a random
sample of 12 men are shown below.
Women 51 55 242 167 152 256 75 137 98 238 235
Men 311 262 170 302 175 320 220 260 72 351 86 333

Carry out a Wilcoxon rank-sum test, at the 5% significance level, to test whether, on average, there is a
difference in cholesterol levels between women and men. [9]

....................................................................................................................................................................
W 51557598137152 167235238242256
....................................................................................................................................................................
12 4 6 7 g f 13 14 15 16
....................................................................................................................................................................

M 12 86 170 175220260 262302 311320933

.................................................................................................................................................................... Est
10 11 12 17 18 19 20 of 22
....................................................................................................................................................................
3 5 2)
....................................................................................................................................................................
o
difference is
Ho :
population median
....................................................................................................................................................................
difference is not 0
H : population median
....................................................................................................................................................................

....................................................................................................................................................................
95 . 5 132
= 2 246
....................................................................................................................................................................
-

1554
....................................................................................................................................................................
- 2 246 - 1 96
.
.

....................................................................................................................................................................

reject Ho
....................................................................................................................................................................
median
Sufficient evidence to support that
population
....................................................................................................................................................................
difference is not 0
....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................

....................................................................................................................................................................
© UCLES 2021 9231/41/O/N/21
CHAPTER 4. NON-PARAMETRIC TESTS 129

8 [9231/w21/42/q4] 8

4 Applicants for a particular college take a written test when they attend for interview. There are two
different written tests, A and B, and each applicant takes one or the other. The interviewer wants
to determine whether the medians of the distribution of marks obtained in the two tests are equal.
The marks obtained by a random sample of 8 applicants who took test A and a random sample of
8 applicants who took test B are as follows.

Test A 46 32 29 12 33 18 25 40
Test B 36 28 49 37 48 35 41 31

(a) Carry out a Wilcoxon rank-sum test at the 5% significance level to determine whether there is a
difference in the population median marks obtained in the two tests. [6]

The interviewer considers using the given information to carry out a paired sample t-test to determine
whether there is a difference in the population means for the two tests.

(b) Give two reasons why it is not appropriate to use this test. [2]

29 33
(a) A 12 18 - 32 40 46

14
12357 g 12

B 28 21353627 414849
4 69 10 11 13 1516

is o
Ho difference
:
population median

not
H difference is o
,: population median

............................................................................................................................................................
5249
............................................................................................................................................................
accept Ho
............................................................................................................................................................
insufficient evidence to support that
population median
............................................................................................................................................................

difference is not o
............................................................................................................................................................

(b)............................................................................................................................................................
unknown
population
............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

© UCLES 2021 9231/42/O/N/21

130 CHAPTER 4. NON-PARAMETRIC TESTS

9 [9231/s20/41/q2] 3

2 The times, in milliseconds, taken by a computer to perform a certain task were recorded on 10 randomly
chosen occasions. The times were as follows.

6.44 6.16 5.62 5.82 6.51 6.62 6.19 6.42 6.34 6.28

It is claimed that the median time to complete the task is 6.4 milliseconds.

(a) Carry out a Wilcoxon signed-rank test at the 5% significance level to test this claim. [6]

(b) State an underlying assumption that is made when using a Wilcoxon signed-rank test. [1]

6 40
19) Ho : population median is .

is not 6 40
Hi population median
.

0 . 04 -0024 10
78-0
.
. 58 00 0022 -0 .
210 . 02 of-al

8
2 +
94 + 1 + 5
-

o
7
-
-

4 +7 + 2 + 1 = 14 .

1478
acceptHo

insufficient evidence

distributed
Lb)
symmetrically
............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................
© UCLES 2020 9231/41/M/J/20 [Turn over
132 CHAPTER 4. NON-PARAMETRIC TESTS

11 [9231/w20/41/q2] 3

2 Metal rods produced by a certain factory are claimed to have a median breaking strength of 200 tonnes.
For a random sample of 9 rods, the breaking strengths, measured in tonnes, were as follows.

210 186 188 208 184 191 215 198 196

4
10 +4 12 8 16
915 2 -
-
- -

A scientist believes that the median breaking strength of metal rods produced by this factory is less than
200 tonnes.

(a) Use a Wilcoxon signed-rank test, at the 5% significance level, to test whether there is evidence to
support the scientist’s belief. [6]

(b) Give a reason why a Wilcoxon signed-rank test is preferable to a sign test, when both are valid.
[1]
4
(a) 10 +4 12 8 16
915 2
-
-
- -

5 -

7 -
63 -

9 - 4 8 - -
2

Ho :
population median is 200

median is less than 200

H1 :
population

1678

accept Ho

evidence
insufficient
............................................................................................................................................................
(b) ............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

© UCLES 2020 9231/41/O/N/20 [Turn over

CHAPTER 4. NON-PARAMETRIC TESTS 133

12 [9231/w20/42/q2] 3

2 A large school is holding an essay competition and each student has submitted an essay. To ensure
fairness, each essay is given a mark out of 100 by two different judges. The marks awarded to the
essays submitted by a random sample of 12 students are shown in the following table.

Student A B C D E F G H I J K L
Judge 1 62 74 52 48 68 55 56 64 37 70 81 59
Judge 2 65 70 47 49 76 74 67 54 50 77 72 75
-

34 5 9 +8110 13 7+ -
- -

9
+

6
(a) One of the students claims that Judge 2 is awarding higher marks than Judge 1.

Carry out a Wilcoxon matched-pairs signed-rank test at the 5% significance level to test whether
the data supports the student’s claim. [7]

It is discovered later that the marks awarded to student A have been entered incorrectly. In fact, Judge 1
awarded 65 marks and Judge 2 awarded 62 marks.

(b) By considering how this change affects the test statistic, explain why the conclusion of the test
carried out in part (a) remains the same. [2]

(a) -

345 +8 + 9 -

110
-

1 +
9
-

234 -1 6 1
+2
98 - 10 57
-
-
- -
=

Ho difference is
3 + 4 + 8 + 7 22
population median
= :

H: difference
22 > 7
population median is

less than o
accept Ho
insufficient evidence

(b)

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................

............................................................................................................................................................
© UCLES 2020 9231/42/O/N/20 [Turn over