LUBS267001

UNIVERSITY OF LEEDS
January 2016

Examination for the degree of

BA and BSc

STATISTICS FOR BUSINESS AND ECONOMICS 2

ANSWERS
QUESTION ANSWER QUESTION ANSWER
1 A 31 E
2 A 32 A
3 B 33 A
4 C 34 D
5 E 35 C
6 C 36 D
7 E 37 C
8 B 38 A
9 B 39 E
10 B 40 C
11 D 41 E
12 A 42 C
13 D 43 A
14 B 44 D
15 D 45 C
16 D 46 A
17 C 47 B
18 D 48 C
19 D 49 D
20 B 50 C
21 D 51 C
22 B 52 B
23 A 53 A
24 E 54 C
25 D 55 C
26 A 56 A
27 A 57 B
28 B 58 A
29 C 59 C
30 C 60 B

2
1. We can use the following property of a joint probability distribution:

  f  x, y   1
x y

i.e. the sum of all probabilities is equal to 1.

 
In our case f  x, y   c 1 
1 2 1
y  x  x y2  , x  0, 2, 3, y  0, 1, 3, 5 . So we
 21 7 
have

3 5
 1 1 2
  c 1  21 y
x 0 y 0
2
x
7
xy  1


3 5
 1 2 1  3 5
 1 1 2

x  0 y 0
c 1 
 21
y  x  x y2   c 
7  x 0
 1  21 y
y 0
2
x
7
xy  


 3 5 1 3 5 3 5
1 3 5 
 c   1    y2   x  x  y 2  
 x 0 y 0 21 x 0 y 0 x 0 y 0 7 x 0 y 0 

 3 1 3 3
1 3 
 c  41   35   4 x    x 35 
 x 0 21 x 0 x 0 7 x 0 

 3 1 3 3 3

 c  4   5  4 x  5 x  
 x 0 3 x 0 x 0 x 0 

 
 c 34   35  45  55  c 12  5  20  25  62 c
1
 3 

1
 62 c  1  c 
62

The joint probability distribution of X and Y is therefore:

1  
f  x, y  
1 2 1
1  y  x  x y2 , x  0, 2, 3, y  0, 1, 3, 5 .
62  21 7 

ANSWER: A

2. If X and Y are discrete random variables and f  x, y  is their joint probability

distribution, the general definition of marginal distribution of X is

3
 f  x    f  x, y  for x  x1 , x 2 , ..., x n
y

 
In our case f  x, y   c 1 
1 2 1
y  x  x y2  , x  0, 2, 3, y  0, 1, 3, 5 . So we
 21 7 
have

5
 
f  x    c 1 
1 2 1
y  x  x y2 
y 0  21 7 

ANSWER: A

5
 
f  x    c 1 
1 2 1
3. y  x  x y2  
y 0  21 7 

5
1  1 2 1 
 1  y  x  x y2  
y 0 62  21 7 

1  5 1 5 5
1 5 
   1   y 2   x  x y 2  
62  y 0 21 y 0 y 0 7 y 0 

1   1  
4 1  35  4 x   x 35 
1 1 5
   4   4 x  5x  
62  21 7  62  3 

1  17 2 17 9
   9x    x
62  3  186 62

Therefore, the marginal distribution of X is

f x  
17 9
 x, x  0, 2, 3
186 62

ANSWER: B

4. If X and Y are discrete random variables and f  x, y  is their joint probability

distribution, the general definition of marginal distribution of Y is

f  y    f  x, y  for y  y1 , y 2 , ..., y m
x

4
  
In our case f  x, y   c 1 
1 2 1
y  x  x y2  , x  0, 2, 3, y  0, 1, 3, 5 . So we
 21 7 
have

3
 
f  y    c 1 
1 2 1
y  x  x y2 
x 0  21 7 

ANSWER: C

3
 
f  y    c 1 
1 2 1
5. y  x  x y2  
x 0  21 7 

3
1  1 2 1 
 1  y  x  x y2  
x 0 62  21 7 

1  3 1 3 3
1 3

  1   y2   x  y2  x 
62  x 0 21 x 0 x 0 7 x 0 

3 1  3 y 2   5  y 2 5 

1  1 1  1  1 2 5 2
  3  y  5  y  
62  21 7  62  7 7 

1  6 2 1  3 2 4 3 2
 8  y    4  y    y
62  7  31  7  31 217

Therefore, the marginal distribution of Y is

f y 
4 3 2
 y , y  0, 1, 3, 5
31 217

ANSWER: E

6. The formula for the required conditional distribution is

f  X  0, y 
f  y X  0 
f  X  0

 
In our case, f  x, y   y  x  x y 2  and f x  
1 1 2 1 17 9
1   x . So we
62  21 7  186 62
have

5
  2 1  1 2
1  21 y  0  7 0  y  62 1  21 y 
1 1 2 1
f  X  0, y 
f  y X  0 
62
  
f  X  0 17

9
0 1  17 
 
186 62 62  3 

3  1 2 3 31  3 1 1 
 1  y    y2     y2  
17  21  17 17  21  17 17  7 

3 1 2
  y
17 119

Therefore, the conditional probability distribution of Y , the number of suggestions

made per week by male employees, when X  0 – i.e. when female employees make
no suggestions – is

f  y X  0 
3 1 2
 y , y  0, 1, 3, 5
17 119

ANSWER: C

5 5
 4 3 2
7. E Y    y  f  y    y   y 
y 0 y 0  31 217 

5
 4 3 3 4 5 3 5 3
 y y   217 
y  y 
y 0  31 217  31 y 0 y 0


4
9  3 153  36  459  252  459  711  3.276
31 217 31 217 217 217 217

ANSWER: E

 3 1 2
E Y X  0    y  f  y X  0   y  
5 5
8. y 
y 0 y 0  17 119 

5
 3 1 3 3 5 1 5 3
  y y   y y 
y 0  17 119  17 y 0 119 y 0


3
9  1 153  27  153  189  153  342  2.874
17 119 17 119 119 119 119

ANSWER: B

6
9. In general, the probability density function (pdf ) of a continuous random variable X
following a (negative) exponential distribution is

f  x    e  x , x  0,   0

As the expected value (mean) of the negative exponential distribution of X is given

by

EX  
1 1
then   
 EX 

In our case the mean (expected value) of patient waiting time is E  X   1.4 ,
therefore:

1 1
   0.714
E  X  1.4

So the pdf of X is

f  x   0.714 e  0.714 x , x0

ANSWER: B

10. f  x   0.714 e  0.714 x , x0

equation of a (negative) exponential function.

Since e  2.718...  0 , the expression e  0.714 x is also positive for any value x .
Therefore

f x   0  x, x  0

i.e. f x  is positive.

First derivative of f x  with respect to x :

df  x  de g  x 
f ' x    0.714  0.714 e  0.714 x    0.714 2  e  0.714 x recall :  g ' x  e g  x 
dx   dx

Therefore

f ' x   0  x, x  0

7
 i.e. f x  is decreasing.

Second derivative of f x  with respect to x :

d 2 f x 
f ' ' x    0.714 2  0.714 e  0.714 x   0.714 3  e  0.714 x
dx 2
 

Therefore

f ' ' x   0  x, x  0

i.e. f x  is convex.

0.714

x  0  f  x   0.714 e 0  0.714 1  0.714

x    f  x   0.714 e  
1
 0.714  0
e

0 x

ANSWER: B

11. The standard deviation of the negative exponential distribution of X is given by

SD  X   var  X  
1 1

 2


In our case:

SD  X  
1
 1.4


ANSWER: D

12. The mean number of patients treated per unit of time, i.e. the mean number of patients
treated per hour, is the mean occurrence rate:

8
 1

EX 

In our case:

1 1
   0.714 mean number of patients treated per hour
E  X  1.4

Therefore, if a hospital A&E department operates a 24-hour working day

0.714  24  17.143 mean number of patients treated per working day

ANSWER: A

13. We use the property of the pdf f x  :

b
Pa  X  b    f  x  dx
a

In our case, the probability that patient waiting time will be longer than 4 hours is

4
P  X  4   1  P 0  X  4   1   e
 x
dx 
x 0

4 4

 0.714 e dx  1  0.714  e  0.714 x dx 

 0.714 x
 1
x 0 x 0

 
4

 1  0.714 
1
e  0.714 x   1  e  0.714 x
 4
0  recall: e
cx
dx 
1 cx
e
 0.714 0 c

 
 1  e  0.714 4   e  0.714 0   1  e  2.857  e 0  

 1  0.057  1  0.057

(using a calculator to evaluate e  2.857  0.057 ).

ANSWER: D

5 5 5
14. P 4  X  5    e dx 
 x
 0.714 e
 0.714 x
dx  0.714  e  0.714 x dx 
x 4 x 4 x 4

9
  
5

 0.714 
1
e  0.714 x    e  0.714 x  4 
 5

 0.714 4

 
  e  0.714 5   e  0.714 4    e 3.571  e 2.857  

  0.028  0.057     0.029   0.029

(using a calculator to evaluate e  3.571  0.028 and e  2.857  0.057 ).

ANSWER: B

15. If X and Y are continuous random variables and f  x, y  is their joint probability
distribution, the general definition of marginal distribution of X is

d
f x    f x, y  dy for a xb
y c

In our case, f  x, y   x y  2 x  2 y  4 ,  0.03  x  0.03 ,  0.15  y  0.15 .

125
9
So we have

0.15
f x   x y  2 x  2 y  4 dy
125

y  0.15
9

ANSWER: D

0.15
f x   x y  2 x  2 y  4 dy
125
16. 
y  0.15
9

0.15 0.15
 
125
x  2  y  2 dy  125 x  2   y  2 dy 
y  0.15
9 9 y  0.15

0.15


125
x  2    2 y  
 y2
9 2  0.15

 
x  2   0.15  20.15   ( 0.15)  2( 0.15)  
2 2
125

9  2   2 

10
 x  2  0.15  0.30  0.15  0.30   125 x  2 0.60 
2 2
125

9  2 2  9


75
x  2  25 x  2
9 3

Therefore, the marginal distribution of X is

f x   x  2 ,
25
 0.03  x  0.03
3

ANSWER: D

0.03

17. EX    x f  x  dx 
x  0.03

0.03
25  x 3 x2 
 
0.03 0.03
x   x  2  dx 
25 25
       
2

3  3 2  0.03
x 2 x dx 2
x  0.03
3 3 x  0.03

25  0.033 2  ( 0.03) 3 2

 
  0.03  
    ( 0.03) 
 
3  3   3 

25  0.033 0.033 
   0.03 
2
 0.032  
3  3 3 

25  0.033 0.033  25  0.033  50

 
3  3
  
3  3 
 2   
3  9
0.033  
50
9
0.000027 

0.00135
  0.00015
9

ANSWER: C

E X 2  
0.03

18.  x 2 f  x  dx 
x  0.03

0.03
25  x 4 x3 
 x  2 x dx  3  4  2  3  
0.0.3 0.03
x   x  2  dx 
25 25
 
2 3 2

x  0.03
3 3 x  0.03 0.03

11
 25  0.034 0.033   ( 0.03) 4 ( 0.03) 3 
    2      2   
3  4 3   4 3 

25  0.034 0.033 0.034 0.033 

   2   2 
3  4 3 4 3 

25  0.033 0.033  25  0.033  100


3 
 2 
3
 2  
3  3 
 4   
3  9
0.033  
100
9
0.000027 

0.0027
  0.00030
9

ANSWER: D

19.  
var X   E X 2  E  X  
2

 0.00030  0.000152  0.00030  0.0000000225 

 0.0002999775  0.00030

ANSWER: D

20. If X and Y are continuous random variables and f  x, y  is their joint probability
distribution, the general definition of marginal distribution of Y is

b
f y   f x, y dx for c yd
xa

In our case, f  x, y   x y  2 x  2 y  4 ,  0.03  x  0.03 ,  0.15  y  0.15 .

125
9
So we have

0.03
f y  x y  2 x  2 y  4 dx
125

x  0.03
9

ANSWER: B

0.03
f y  x y  2 x  2 y  4 dx
125
21. 
x  0.03
9

12
 0.03 0.03
 
125
x  2  y  2 dx  125  y  2  x  2 dx 
x  0.03
9 9 x  0.03

0.03

 y  2   x  2 x  
2
125

9 2  0.03

 
 y  2   0.03  20.03   ( 0.03)  2( 0.03)  
2 2
125

9  2   2 

 y  2  0.03  0.06  0.03  0.06   125  y  2 0.12 

2 2
125

9  2 2  9


15
 y  2  5  y  2
9 3

Therefore, the marginal distribution of Y is

f y   y  2 ,
5
 0.15  y  0.15
3

ANSWER: D

0.15
22. E Y    y f  y  dy 
y  0.15

0.15
5  y3 y2 
 
0.15 0.15
y   y  2  dy 
5 5
       
2
y 2 y dy 3 2 
y  0.15
3 3 y  0.15
3  2  0.15

5  0.153 2  ( 0.15) 3 
 
  0 .15 
    ( 0.15) 2  
3  3   3 

5  0.153 0.153 
   0.152   0.152  
3 3 3 

5  0.153 0.153  5  0.153  10

  0.153   0.003375 
10
     2 
3 3 3  3 3  9 9

0.03375
  0.00375
9

13
 ANSWER: B

E Y  
0.15
23. 2
y 2 f  y  dy 
y  0.15

0.15
5  y4 y3 
 
0.15 0.15
y   y  2  dy 
5 5
       
2 3 2
y 2 y dy 4 2 
y  0.15
3 3 y  0.15
3  3  0.15

5  0.154 0.153   ( 0.15) 4 ( 0.15) 3 

   2   2  
3  4 3   4 3 

5  0.154 0.153 0.154 0.153 

   2   2 
3 4 3 4 3 

5  0.153 0.153  5  0.153  20

  2 
3 3
 2
3 

3
 4   
3  9
0.153  
20
9
0.003375 

0.0675
  0.00750
9

ANSWER: A

var Y   E Y 2   E Y  
2
24.

 0.00750  0.003752  0.00750  0.0000140625 

 0.0074859375  0.00749

ANSWER: E

25. If X and Y are continuous random variables and f  x, y  is their joint probability
distribution, the general definition of expected value of the product of X and Y is

b d
E  XY     xy f x, y  dy dx
x  a y c

14
 In our case, f  x, y   x y  2 x  2 y  4 ,  0.03  x  0.03 ,  0.15  y  0.15 .
125
9
So we have

0.03 0.15
E  XY   x y  2 x  2 y  4 dy dx 
125

x  0.03

y  0.15
xy 
9

x y  2 x 2 y  2 xy 2  4 xy dy dx
0.03 0.15
125 2 2
 
x  0.03

y  0.15
9

ANSWER: D

26. Let us first check for the possible independence of the random variables X and Y .
To check for independence of X and Y , it is necessary to verify whether
f  x  f  y   f  x, y  for any values x and y within their ranges of definition:

f x  f  y   f x, y   x, y within their ranges of definition

Since we know from answers 16 and 21 that

f x   x  2 , f  y   5  y  2 and f  x, y   x y  2 x  2 y  4 
25 125
3 3 9

we have

 25  5  125
f  x  f  y     x  2     y  2   x  2 y  2 
3  3  9


125
x y  2 x  2 y  4   f x, y  ,   0.03  x  0.03,  0.15  y  0.15
9

Therefore, X and Y are independent.

As a consequence of the independence of X and Y

E  XY   E  X E Y 

We know from answers 17 and 22 that E  X   0.00015 and E Y   0.00375 .

Therefore

E  XY   0.00015  0.00375  0.0000005625  0.000001

ANSWER: A

15
27. As a consequence of the independence of X and Y

E  XY   E  X E Y   E  XY   E  X E Y   0

Therefore

cov  X , Y   E  XY   E  X E Y   0

ANSWER: A

28. As a consequence of the independence of X and Y

cov  X , Y   0

Therefore

cov X , Y  0
X ,Y   0
SD  X  SD Y  SD X  SDY 

ANSWER: B

29. We can apply the formula for the expected value of the sum of two functions of X
and Y :

E g1  X   g 2 Y    E g1  X    E g 2 Y  

In our case, g1  X   0.10 X and g 2 Y   0.90Y .

We know from answers 17 and 22 that E  X   0.00015 and E Y   0.00375 . So

for the expected value of the rate of return of the portfolio R we have:

E R   E 0.10 X  0.90Y  

 E 0.10 X   E 0.90Y  

 0.10 E  X   0.90 E Y  

 0.10 0.00015   0.90 0.00375  

 0.000015  0.003375  0.00339

ANSWER: C

16
30. If a  bX  is a linear combination of X , c  dY  is a linear combination of Y , and
R is their sum, i.e., R  a  bX   c  dY  – where a, b, c and d are constants – the
variance of R , var R  , is given by the formula for the variance of linear
combinations of two random variables:

varR  b2 var X   d 2 varY   2 b d cov X , Y 

Since R  0.10 X  0.90Y , in our case a  0 , b  0.10 , c  0 and d  0.90 . We

know from answers 19, 24 and 27 that var  X   0.00030 , var Y   0.00749 and
cov  X , Y   0 . So we have:

varR   0.102 var X   0.902 varY   2 0.100.90 cov X , Y  

 0.01 0.00030   0.81 0.00749   0 

 0.000003  0.006067  0.00607

ANSWER: C

31. For the test of the hypothesis that the population mean output per worker per day
(productivity) on Fridays and on days between Monday and Thursday is the same,
against the alternative hypothesis that the population mean output per worker per day
on Fridays is smaller than that on days between Monday and Thursday, i.e. that
productivity drops on Friday, the null and alternative hypotheses are:

H 0 : 1   2 H 1 : 1   2

that is

H 0 : 1   2  0 H 1 : 1   2  0

ANSWER: E

32. For the large sample of workers observed on Fridays ( n1  50) taken from a finite
population ( N  560) without replacement, the sampling ratio is:

n1 50
  0.089  0.10 (10%)
N 560

Therefore we do not need to use the finite population correction of the variance.

17
 For the large sample of workers observed on days between Monday and Thursday (
( n 2  70 ) taken from a finite population ( N  560) without replacement, the
sampling ratio is:

n2 70
  0.125  0.10 (10%)
N 560

 N  n2 
Therefore we need to use the finite population correction of the variance:  .
 N 1 

The two samples are independent. Sampling theory establishes that the sampling
distribution of the difference between the two sample means X 1  X 2  is:

  2  2  N  n2  
( X 1  X 2 ) ~ N  1   2 , 1  2  
 n1 n2  N  1  

The population variances  12 and  22 are known. Therefore the test statistic is given
by

( X 1  X 2 )  ( 1   2 ) 0
 12  22  N  n2 
  
n1 n2  N  1 

ANSWER: A

33. It is known that, for workers observed on Fridays, the sample size is n1  50 , the
finite population size is N 1  N  560 , the sample mean output per worker per day is
X 1  66.6 units, and its population variance is  12  55.5 ; for workers observed on
days between Monday and Thursday, the sample size is n2  70 , the finite population
size is N 2  N  560 , the sample mean output per worker per day is X 2  68.8 units,
and its population variance is  22  58.7 . It is also known that the difference between
population means under the null hypothesis is ( 1   2 ) 0  0 . So the value of the test
statistic is:

( X 1  X 2 )  ( 1  2 ) 0 (66.6  68.8)  (0)

 
 12  22  N  n2  55.5 58.7  560  70 
     
n1 n2  N  1  50 70  560  1 

 2 .2
 
55.5 58.7  490 
  
50 70  559 

18
  2 .2
 
1.11  0.8385710.876565

 2.2  2.2
   1.6196
1.84506 1.35833

ANSWER: A

34. Since the sampling distribution of the difference between the two sample means
X 1  X 2  is normal:
  2  2  N  n2  
( X 1  X 2 ) ~ N  1   2 , 1  2  
 n1 n2  N  1  

the test statistic follows the standard normal distribution:

( X 1  X 2 )  ( 1   2 ) 0
 Z ~ N 0, 1
 12  22  N  n2 
  
n1 n2  N  1 

ANSWER: D

35. The test statistic follows the standard normal distribution:

Z ~ N 0, 1

Since the alternative hypothesis takes the form H 1 : 1   2  0 , the test is one-
tailed (left-hand side tail).

The required significance level is   5% .

Therefore, the critical value for the test is:

z0.95  1.6449

19
 5% 1

95%

Z
 1.6449 0

ANSWER: C

36.

5% 1

95%

Z
 1.6449 0

Reject Do not
H0 reject H 0

 if Z  1.6449 , reject H 0
 if Z  1.6449 , do not reject H 0

ANSWER: D

37. Since the test statistic Z  1.6196  1.6449 , we do not eject H 0 : 1   2 at the
5% significance level in favour of the alternative H 1 : 1   2 . There is no
significant evidence (at the 5% level) that the population mean output per worker per
day (productivity) on Fridays ( 1 ) is smaller than that on days between Monday and
Thursday (  2 ) , i.e. there is no significant evidence that productivity drops on Friday.

ANSWER: C

38. For the test of the hypothesis that the variability of weekly deposits has remained the
same, against the alternative hypothesis that it has changed – ie, for the test of the
hypothesis that the population standard deviation of weekly deposits is equal to
£14,142, against the alternative hypothesis that it is different from £14,142, the null
and alternative hypotheses are:

20
 H 0 :   14,142 H 1 :   14,142

that is, in terms of the population variance

H 0 :  2  14,142 2 H 1 :  2  14,142 2 or

H 0 :  2  199,996,164 H 1 :  2  199,996,164

ANSWER: A

39. It is known that the random variable X (weekly deposits) is normally distributed
and that the sample is small ( n  13 ). The object of our inference is the population
variance  2 .

Therefore the test statistic is given by

n  1 s 2
 02

ANSWER: E

40. It is known that the sample standard deviation of weekly deposits is s  21,512 , the
sample size n  13 , and the population standard deviation under the null hypothesis
 0  14,142 . So the value of the test statistic is:

n  1 s 2 
13  1 21,512 2

12  462,766,144  5,553,193,728  27.767
 2
0 14,142 2
199,996,164 199,996,164

ANSWER: C

41. It is known that the random variable X (weekly deposits) is normally distributed
and that the sample is small ( n  13 ).

Therefore the test statistic follows the  2 distribution:

n  1 s 2   2 ~  2 distribution with   n  1  13  1  12 degrees of freedom

 2
0

ANSWER: E

21
42. The test statistic follows the  2 distribution:

 2 ~  2 distribution with   12 degrees of freedom

Since the alternative hypothesis takes the form H 1 :  2  199,996,164 , the test is
two-tailed.

The required significance level for the test is   1% .

Therefore, the critical values for the test are:

 02.995, 12  3.074 ,  02.005, 12  28.300

0.5% 99% 0.5%

0
3.074 28.300
122

ANSWER: C

43.

0.5% 99% 0.5%

0
3.074 28.300
122

Reject Do not Reject

H0 reject H 0 H0

 if  2  3.074 or  2  28.300 , reject H 0

 if 3.074   2  28.300 , do not reject H 0

ANSWER: A

22
44. Since the test statistic 3.074   2  27.767  28.300 , we do not reject
H 0 :   14,142 at the 1% significance level in favour of the alternative
H 1 :  2  14,142 . There is no significant evidence (at the 1% level) that the
population standard deviation of weekly deposits is different from £14,142 – ie, there
is no significant evidence (at the 1% level) that the variability of weekly deposits has
changed.

ANSWER: D

45. For the large sample of car owners in Amsterdam ( n1  2200 ) taken from a finite
population ( N 1  220000 ) without replacement, the sampling ratio is:

n1 2200
  0.01  0.10 (10%)
N1 220000

Therefore we do not need to use the finite population correction of the variance.

Sampling theory establishes that the sampling distribution of the sample proportion P1
of hybrid-electric car owners in Amsterdam is:

  1   1  
P1 ~ N   1 , 1 
a
 n1 

ANSWER: C

46. From the sampling distribution of the sample proportion P1 , the standard error of the
sample proportion P1 is:

 1 1   1 
SE P1  
n1

The population proportion  1 is unknown. So we use the sample proportion P1 , the

unbiased point estimator of  1 , in estimating the standard error of the sample
proportion P1 :

P1 1  P1 
SE P1  
n1

It is known that the sample proportion of hybrid-electric car owners in Amsterdam is

P1  0.057 (5.7%) and the sample size n1  2200 . The standard error of the sample
proportion P1 is therefore:

23
 P1 1  P1  0.057 1  0.057  0.057 0.943
SE P1  
0.053751
    0.0049
n1 2200 2200 2200

ANSWER: A

47. The 95% confidence interval for the population proportion  1 of hybrid-electric car
owners in Amsterdam is given by

P1 1  P1 
 1  P1  z0.025 SE P1   P1  z0.025
n1

ANSWER: B

48. From the distribution of the standard normal random variable Z ~ N 0, 1 we have

2.5% 1 2.5%
95%

0 Z
 1.9600 1.9600

The critical value corresponding to the 95% confidence level is therefore:

z 0.025  1.9600

ANSWER: C

49. It is known that the sample proportion of hybrid-electric car owners in Amsterdam is
P1  0.057 (5.7%) , the critical value corresponding to the 95% confidence level

z 0.025  1.9600 , and SE P1  

0.053751
 0.0049 . So the 95% confidence interval
2200
for the population proportion  1 is:

 1  P1  z 0.025 SE P1   0.057  1.9600  0.057  1.9600 0.0049  

0.053751
2200

 0.0473, 0.0667 

24
 ANSWER: D

50. The population proportion of hybrid-electric car owners in Amsterdam is some value
between 0.0473 and 0.0667 with a 95% probability. Since this interval does not
include the value 0.08, the confidence interval obtained does not include the
possibility that in Amsterdam the population proportion of hybrid-electric car owners
is 8%, as claimed. There is no evidence (with 95% confidence) in favour of the
claim.

ANSWER: C

51. For the test of the null hypothesis that the population proportion of hybrid-electric car
owners in Vienna (  2 ) is the same as in Amsterdam (  1 ), against the alternative
hypothesis that the population proportion of hybrid-electric car owners in Vienna is
smaller than in Amsterdam, the null and alternative hypotheses are:

H0 :  2  1 H1 :  2   1

that is

H0 : 1   2  0 H1 :  1   2  0

ANSWER: C

52. For the large sample of car owners in Amsterdam ( n1  2200 ) taken from a finite
population ( N 1  220000 ) without replacement, the sampling ratio is:

n1 2200
  0.01  0.10 (10%)
N1 220000

Therefore we do not need to use the finite population correction of the variance.

For the large sample of car owners in Vienna ( n 2  3100 ) taken from a finite
population ( N 2  314000 ) without replacement, the sampling ratio is:

n2 3100
  0.0099  0.10 (10%)
N 2 314000

Therefore we do not need to use the finite population correction of the variance.

Sampling theory establishes that the sampling distribution of the difference between
the two sample proportions P1  P2  is:

25
 P1  P2  ~a N   1   2 ,  1 1   1    2 1   2  
 
 n1 n2 

ANSWER: B

53. The population proportions  1 and  2 are unknown. So we use the sample
proportions P1 and P2 , the unbiased point estimators of  1 and  2 , in estimating the
standard error of the difference between the two sample proportions P1  P2  ,
SE P1  P2  .

Therefore the test statistic is given by

P1  P2    1   2 0 P1  P2    1   2 0

P1 1  P1  P2 1  P2 
SE P1  P2  
n1 n2

It is known that, for Amsterdam, the sample proportion of hybrid-electric car owners
is P1  0.057 (5.7%) and the sample size n1  2200 ; for Vienna, the sample
proportion of hybrid-electric car owners is P2  0.043 ( 4.3%) and the sample size
n2  3100 . It is also known that the difference between population proportions under
the null hypothesis is  1   2 0  0 . So the value of the test statistic is:

P1  P2    1   2 0 0.057  0.043  0

 
P1 1  P1  P2 1  P2  0.057 1  0.057  0.043 1  0.043
 
n1 n2 2200 3100

0.014
 
0.057 0.943 0.043 0.957 

2200 3100

0.014
 
0.053751 0.041151

2200 3100

0.014 0.014
   2.2799
0.000024  0.000013 0.000038

ANSWER: A

26
54. Since the sampling distribution of the difference between the two sample proportions
P1  P2  is normal:

P1  P2  ~a N   1   2 ,  1 1   1    2 1   2  
 
 n1 n2 

the test statistic follows the standard normal distribution:

P1  P2    1   2 0
 Z ~ N 0, 1
P1 1  P1  P2 1  P2 

n1 n2

Since the alternative hypothesis takes the form H 1 :  1   2  0 , the test is one-
tailed (right-hand side tail).

The required significance level is   5% .

Therefore, the critical value for the test is:

z0.05  1.6449

1 5%
95%

0 Z
1.6449

ANSWER: C

55.

1 5%
95%

0 Z
1.6449

Do not Reject
reject H 0 H0

27
  if Z  1.6449 , reject H 0
 if Z  1.6449 , do not reject H 0

ANSWER: C

56. Since the test statistic Z  2.2799  1.6449 , we reject H 0 :  2   1 at the 5%

significance level in favour of the alternative H 1 :  2   1 . There is significant
evidence (at the 5% level) that the population proportion of hybrid-electric car
owners in Vienna (  2 ) is smaller than in Amsterdam (  1 ).

ANSWER: A

57. Since the sampling distribution of the difference between the two sample proportions
P1  P2  is normal:

P1  P2  ~a N   1   2 ,  1 1   1    2 1   2  
 
 n1 n2 

the test statistic follows the standard normal distribution:

P1  P2    1   2 0
 Z ~ N 0, 1
P1 1  P1  P2 1  P2 

n1 n2

Since the alternative hypothesis takes the form H 1 :  1   2  0 , the test is one-
tailed (right-hand side tail).

The required significance level is   1% .

Therefore, the critical value for the test is:

z 0.01  2.3263

1
1%
99%

0 Z
2.3263

28
 ANSWER: B

58.

1
1%
99%

0 Z
2.3263

Do not Reject
reject H 0 H0

 if Z  2.3263 , reject H 0
 if Z  2.3263 , do not reject H 0

ANSWER: A

59. Since the test statistic Z  2.2799  2.3263 , we do not reject H 0 :  2   1 at the
1% significance level in favour of the alternative H 1 :  2   1 . There is no
significant evidence (at the 1% level) that the population proportion of hybrid-electric
car owners in Vienna (  2 ) is smaller than in Amsterdam (  1 ).

ANSWER: C

60. The evidence against the null hypothesis H 0 :  2   1 and in favour of the
alternative hypothesis H 1 :  2   1 is not very strong: H 0 is rejected at the 5% , but
not at the 1% significance level. So evidence from the study in favour of the claim
that the population proportion of hybrid-electric car owners in Vienna (  2 ) is smaller
than in Amsterdam (  1 ) is not very strong: it would be advisable to select larger
samples.

ANSWER: B

29