CHAPTER 3:

STATISTICAL
INFERENCES (WEEK 9)
3.1 Introduction
3.2 Sampling distribution WEEK 8

3.3 Inference for single population

3.4 Inference for two populations WEEK 9

3.5 Nonparametric statistics WEEK 10

CI FOR 2 POPULATIONS
Example 1:
The scientist wondered whether there was a difference in the average daily intakes
of dairy products between men and women. He took a sample of n =50 adult
women and recorded their daily intakes of dairy products in grams per day. He did
the same for adult men. A summary of his sample results is listed below.
Men Women
Sample size 50 50
Sample mean 780 grams per 762 grams per
day day
Sample standard 35 30
deviation

Construct a 95% confidence interval for the difference in the average daily intakes
of daily products for men and women. Can you conclude that there is a difference
9

in the average daily intakes of daily products for men and women?
Solution:
For 95% CI,
95% = 100(1 –  )%
1 – = 0.95
 = 0.05

= 0.025  z = z0.025 = 1.96
2 2

   ( 35 )
2
( 30 )
2 
(x )
2 2
s s
− x2  z  1
+ 2  = ( 780 − 762 )  1.96  + 
 
1
2  n1 n2   50 50 
 
= 18  12.78
= [5.22, 30.78]
Thus, we conclude that there is a difference in the average daily intakes
of daily products for men and women as 1 −  2 = 0
( there is no difference between two population means ) is not one of the
possible values for (1 −  2 ).
10
 2.1.4 Confidence Interval Estimates For The Differences Between Two
Population Proportion

The (1 −  )100% Confidence Interval for the Differences between

Two Proportions, P1 − P2 , ( n1  30, n2  30)

ˆ1 (1 − p
p ˆ1 ) ˆ 2 (1 − p
p ˆ2 )
( pˆ1 − pˆ 2 )  z 2 +
n1 n2

11
Example 1:
A researcher wanted to estimate the difference between the percentages of users of two toothpastes
who will never switch to another toothpaste. In a sample of 500 users of Toothpaste A taken by this
researcher, 100 said that the will never switch to another toothpaste. In another sample of 400 users
of Toothpaste B taken by the same researcher, 68 said that they will never switch to another
toothpaste. Construct a 97% confidence interval for the difference between the proportions of all
users of the two toothpastes who will never switch.

Solution:
Toothpaste A : n1 = 500 and x1 = 100
Toothpaste B : n2 = 400 and x2 = 68

The sample proportions are calculated;

100 68
ˆ1 =
p = 0.20; p
ˆ2 = = 0.17
500 400 12
For 97% CI,
97% = 100(1 –  )%
1 – = 0.97
 = 0.03

= 0.015  z = z0.015 = 2.17
2 2

A 97% confidence interval ;

 ˆ1 (1 − p
p ˆ1 ) pˆ (1 − p
ˆ2 ) 
=(p ˆ 2 )  Z
ˆ1 − p 
 + 2 

2  n1 n2 
 0.20(0.80) 0.17(0.83) 
= ( 0.20 − 0.17 )  2.17 
 + 

 500 400 
= 0.03  0.05628
= [ −0.026, 0.086]

Thus, with 97% confidence we can state that the difference between the two population
13
proportions is between -0.026 and 0.086.
HYPOTHESIS TESTING
Hypothesis Test For the Difference between Two Populations Means,
Null Hypothesis : H 0 : 1 −  2 = 0
Test statistics:

15
Rejection Region

Alternative hypothesis Rejection Region

H1 : 1 −  2  0 Z  − z 2 or Z  z 2

H1 : 1 −  2  0 Z  z

H1 : 1 −  2  0 Z< − z

18
Example 1:

A university conducted an investigation to determine whether car ownership affects

academic achievement was based on two random samples of 100 male students, each
drawn from the student body. The grade point average for n1 = 100 non owners of
cars had an average and variance equal to as opposed to
= 2.70
for n2 = 100x1car and s =data
owners.
2
Do 1the x2 = 2.54
0.36present sufficient evidence and
to indicate
= 0.40 in the mean achievements between car owners and non-owners of cars?
sa22difference
Test using α = 0.05.

19
Solution:
1.The hypotheses to be tested are:
H 0 : 1 −  2 = 0
H1 : 1 −  2  0

2. z 2 = z0.05 2 = z0.025 = 1.96

Rejection Region : Z  − z 2 or Z  z 2

Do Not
Reject H 0

Reject H 0
Reject H 0

 − 

20

z=-1.96 z=+1.96
3. Therefore, test statistic is

Z test =
( x − x ) − ( −  )
1 2 1 2
=
2.70 − 2.54
= 1.84
2 2
s s2 0.36 0.40
+ 1 +
n1 n2 100 100

4. Since Z test = 1.84 < Z 0.025 =1.96 or Z test = 1.84 > Z 0.025 = − 1.96,
thus we fail to reject H 0 .

5.There is insufficient evidence to support the claim that there is a

difference in the average academic achievement for the two groups.
21
Hypothesis Test For the Difference between Two Population
Proportion, p1 − p2

Null Hypothesis : H 0 : p1 − p2 = 0

Test Statistics :

Z =
( pˆ1 − pˆ 2 ) − ( p1 − p2 ) =
( ˆ 2 ) − ( p1 − p2 )
ˆ1 − p
p
ˆ (1 − p
p ˆ) ˆ (1 − p
p ˆ)  1 1 
+ ˆ ˆ
pq + 
n1 n2  n1 n2 
x1 + x2
ˆ =
where p , qˆ = 1 − p
ˆ
n1 + n2 22
Alternative hypothesis Rejection Region

H1 : p1 − p2  0 Z  − z 2 or Z  z 2

H1 : p1 − p2  0 Z  z

H1 : p1 − p2  0 Z< − z

23
Example 2:

A researcher wanted to estimate the difference between the percentages of users of

two toothpastes who will never switch to another toothpaste. In a sample of 500 users
of Toothpaste A taken by this researcher, 100 said that the will never switch to
another toothpaste. In another sample of 400 users of Toothpaste B taken by the same
researcher, 68 said that they will never switch to another toothpaste. At the
significance level 1%, can we conclude that the proportion of users of Toothpaste A
who will never switch to another toothpaste is higher than the proportion of users of
Toothpaste B who will never switch to another toothpaste?

24
Solution:
1. The hypotheses to be tested are ,
 p1 is equal to p2  No difference 
H 0 : p1 − p2 = 0  
 between p 1 and p2 

H1 : p1 − p2  0 ( p1 is greater than p2 )

2. Critical value z = z0.01 = 2.33

Rejection Region : Ztest  z

3. Test statistic is

Z test =
( pˆ1 − ˆ 2 ) − ( p1 − p2 )
p
=
0.20 − 0.17 − 0
= 1.15
 1 1   1 1 
ˆ ˆ
pq +  (0.187)(0.813)  + 
 1
n n2   500 400 
25
4. Since Z test = 1.15  z0.01 = 2.33, thus we fail to reject H 0 .

5. We conclude that the there is insufficient evidence to support the claim

that proportions of users Toothpaste A who will never switch to another
toothpaste is higher than the proportion of users of Toothpaste B who will
never switch to another.