Chapter 10

Statistical Inferences Based on

Two Samples

McGraw-Hill/Irwin Copyright 2010 by The McGraw-Hill Companies, Inc. All rights reserved.
Chapter Outline
10.1 Comparing Two Population Means by
Using Independent Samples: Variances
Known
10.2 Comparing Two Population Means by
Using Independent Samples: Variances
Unknown
10.3 Paired Difference Experiments
10.4 Comparing Two Population Proportions by
Using Large, Independent Samples
10.5 Comparing Two Population Variances by
Using Independent Samples
10-2
10.1 Comparing Two Population Means
by Using Independent Samples:
Variances Known

Suppose a random sample has been taken

from each of two different populations
Suppose that the populations are
independent of each other
Then the random samples are independent of
each other
Then the sampling distribution of the
difference in sample means is normally
distributed
10-3
Sampling Distribution of the
Difference of Two Sample Means #1
Suppose population 1 has mean 1 and
variance 12
From population 1, a random sample of size n1 is
selected which has mean x1 and variance s12

Suppose population 2 has mean 2 and

variance 22
From population 2, a random sample of size n2 is
selected which has mean x2 and variance s22

Then the sample distribution of the difference

of two sample means
10-4
Sampling Distribution of the
Difference of Two Sample Means #2

Is normal, if each of the sampled

populations is normal
Approximately normal if the sample sizes
n1 and n2 are large
Has mean x1x2 = 1 2
Has standard deviation
12 22
x x
1 2
n1 n2
10-5
 Sampling Distribution of the
Difference of Two Sample Means #3

Figure 10.1 10-6

z-Based Confidence Interval for the
Difference in Means (Variances Known)

A 100(1 ) percent confidence

interval for the difference in populations
12 is
12 22
x1 x2 z 2
n1 n2

10-7
z-Based Test About the Difference in
Means (Variances Known)
Test the null hypothesis about
H0: 1 2 = D0
D0 = 1 2 is the claimed difference
between the population means
D0 is a number whose value varies
depending on the situation
Often D0 = 0, and the null means that
there is no difference between the
population means

10-8
z-Based Test About the Difference in
Means (Variances Known)

Use the notation from the confidence

interval statement on a prior slide
Assume that each sampled population is
normal or that the samples sizes n1 and
n2 are large

10-9
Test Statistic (Variances Known)
The test statistic is
z
x1 x2 D0
12 22

n1 n2

The sampling distribution of this statistic is a

standard normal distribution
If the populations are normal and the
samples are independent ...
10-10
z-Based Test About the Difference in
Means (Variances Known)

Reject H0: 1 2 = D0 in favor of a

particular alternative hypothesis at a
level of significance if the appropriate
rejection point rule holds or if the
corresponding p-value is less than
Rules are on the next slide

10-11
z-Based Test About the Difference in
Means (Variances Known) Continued

10-12
 Example 10.2: The Bank Customer
Waiting Time Case
H 0 : 1 2 0
H a : 1 2 0

z
x1 x2 D0
8.79 5.14 0 14.21
2
2
4.7

1.9
1
2
n1 n2 100 100

10-13
10.2 Comparing Two Population Means
by Using Independent Samples:
Variances Unknown

Generally, the true values of the

population variances 12 and 22 are not
known
They have to be estimated from the
sample variances s12 and s22,
respectively

10-14
Comparing Two Population Means
Continued

Also need to estimate the standard

deviation of the sampling distribution
of the difference between sample
means
Two approaches:
1. If it can be assumed that 12 = 22 = 2,
then calculate the pooled estimate of 2
2. If 12 22, then use approximate
methods
10-15
Pooled Estimate of 2

s 2

n1 1s n2 1s
2
1
2
2
n1 n 2 2
p

1 1
x x s
2
p
n1 n2
1 2

10-16
 t-Based Confidence Interval for the
Difference in Means (Variances
Unknown)

x1 x2 t 2 s p
2 1 1
n1 n2

s 2

n1 1s
2
1 n2 1s 2
2
n1 n 2 2
p

10-17
 Example 10.3: The Catalyst
Comparison Case
n
s2 1
1s1
2
n2 1s 2
2
n1 n 2 2
p

5 1386 5 1484.2
435.1
552

1 1 1 1
x x s 435.1 30.42
2
p
n1 n2 5 5
1 2

x x 811 750.2 30.42 30.38,91.22

1 2 x1 x2 10-18
t-Based Test About the Difference in
Means: Variances Equal
x1 x 2 D0
1 1
s
2
pn n
1 2

10-19
 Example 10.4: The Catalyst
Comparison Case

H 0 : 1 2 0
H1 : 1 2 0

t
x1 x2 D0
811 750.2 0
4.6087
1 1 1 1
s
2
435.1
p
n1 n2 5 5
10-20
t-Based Confidence Intervals and Tests
for Differences with Unequal Variances
s12 s22
x1 x2 t/2
n1 n2

t
x1 x2 D0
s12 s22

n1 n2

df
s /n s /n
2
1 1
2
2 2
2

s /n s /n
2
1 1
2 2
2 2
2

n1 1 n2 1
10-21
10.3 Paired Difference Experiments

Before, drew random samples from two

different populations
Now, have two different processes (or
methods)
Draw one random sample of units and
use those units to obtain the results of
each process

10-22
Paired Difference Experiments Continued

For instance, use the same individuals

for the results from one process vs. the
results from the other process
E.g., use the same individuals to compare
before and after treatments
Using the same individuals, eliminates
any differences in the individuals
themselves and just comparing the
results from the two processes 10-23
Paired Difference Experiments #3
Let d be the mean of population of paired
differences
d = 1 2, where 1 is the mean of population 1
and 2 is the mean of population 2
Let d and sd be the mean and standard
deviation of a sample of paired differences
that has been randomly selected from the
population
d is the mean of the differences between pairs of
values from both samples
10-24
t-Based Confidence Interval for
Paired Differences in Means

sd
d t /2
n

d D0
t=
sd / n
10-25
Paired Differences Testing Rules

10-26
 Example 10.6 and 10.7: The Repair
Cost Comparison Case

sd .5033
d t/2 .8 2.447 1.2654,.3346
n 7

H o : d 0
H a : d 0

d D0 .8 0
t= 4.2053
sd / n .5033 7
10-27
10.4 Comparing Two Population
Proportions by Using Large,
Independent Samples
Select a random sample of size n1 from a
population, and let p1 denote the proportion
of units in this sample that fall into the
category of interest
Select a random sample of size n2 from
another population, and let p2 denote the
proportion of units in this sample that fall into
the same category of interest
Suppose that n1 and n2 are large enough
n1p1 5, n1(1 - p1) 5, n2p2 5, and n2(1
p2) 5

10-28
Comparing Two Population
Proportions Continued

Then the population of all possible

values of p1 - p2
Has approximately a normal distribution if
each of the sample sizes n1 and n2 is large
Has mean p1 - p2 = p1 p2
Has standard deviation

p1 1 p1 p2 1 p2
p1 p2
n1 n2
10-29
 Difference of Two Population
Proportions

p 1 1 p 1 p 2 1 p 2
p 1 p 2 z 2
n1 n2

z=
p 1 p 2 D0
p p
1 2

10-30
 Example 10.9 and 10.10: The
Advertising Media Case
p 1 1 p 1 p 2 1 p 2
p 1 p 2 z 2
n 1 n 2
.631.369 .798.202
.631 .798 1.96
1,000 1,000
.2059,.1281

z=
p 1 p 2 D0

p1 p 2 D0
.631 .798 0
p p 1 1 1 1
1 2
p 1 p .71451 .7145
n1 n2 1,000 1,000
z 8.2673
10-31
10.5 Comparing Two Population
Variances Using Independent Samples
Population 1 has variance 12 and population 2 has
variance 22
The null hypothesis H0 is that the variances are the
same
H0: 12 = 22
The alternative is that one is smaller than the other
That population has less variable measurements
Suppose 12 > 22
More usual to normalize
Test H0: 12/22 = 1 vs. 12/22 > 1

10-32
Comparing Two Population Variances
Using Independent Samples Continued
Reject H0 in favor of Ha if s12/s22 is significantly
greater than 1
s12 is the variance of a random of size n1 from a
population with variance 12
s22 is the variance of a random of size n2 from a
population with variance 22
To decide how large s12/s22 must be to reject H0,
describe the sampling distribution of s12/s22
The sampling distribution of s12/s22 is the F
distribution

10-33
 F Distribution

Figure 10.13 10-34

F Distribution
The F point F is the point on the horizontal
axis under the curve of the F distribution that
gives a right-hand tail area equal to
The value of F depends on a (the size of the
right-hand tail area) and df1 and df2
Different F tables for different values of
Tables A.5 for = 0.10
Tables A.6 for = 0.05
Tables A.7 for = 0.025
Tables A.8 for = 0.01
10-35
 Example 10.11: The Catalyst
Comparison Case

H0 :
2
1
2
2

Ha :
2
1
2
2
2
2
2
1

2
s 484.2
F 2
2
1.2544
s 1 386
10-36