Slides Prepared by

JOHN S. LOUCKS
St. Edward’s University

© 2003 South-Western/Thomson Learning™

1
 Chapter 10
Statistical Inferences about Means
and Proportions for Two Populations
 Estimation of the Difference Between the Means of
Two Populations: Independent Samples
 Hypothesis Tests about the Difference Between the
Means of Two Populations: Independent Samples
 Inferences about the Difference Between the Means
of Two Populations: Matched Samples
 Inferences about the Difference Between the
Proportions of Two Populations

© 2003 South-Western/Thomson Learning™

2
 Estimation of the Difference between the
Means of Two Populations: Independent
Samples
 Point Estimator of the Difference between the
Means of Two Populations
x1  x2
 Sampling Distribution
 Interval Estimate of Large-Sample Case
 Interval Estimate of Small-Sample Case

© 2003 South-Western/Thomson Learning™

3
Point Estimator of the Difference between
the Means of Two Populations
 Let 1 equal the mean of population 1 and 2
equal the mean of population 2.
 The difference between the two population
means is 1 - 2.
 To estimate 1 - 2, we will select a simple
random sample of size n1 from population 1
and a simple random sample of size n2 from
x1 x2
population 2.
 Let equal the mean of sample 1 and
equal the mean of sample 2.
x1  x2
 The point estimator of the difference between
the means of the populations 1 and 2 is
.
© 2003 South-Western/Thomson Learning™
4
 Sampling Distribution of x1  x2

 x1  x2
Properties of the Sampling Distribution of
• Expected Value
E ( x1  x2 ) 1   2
• Standard Deviation
12  22
 x1  x2  
n1 n2
where: 1 = standard deviation of population 1
2 = standard deviation of population 2
n1 = sample size from population 1
n2 = sample size from population 2
© 2003 South-Western/Thomson Learning™
5
 Interval Estimate of 1 - 2:
Large-Sample Case (n1 > 30 and n2 > 30)

 Interval Estimate with 1 and 2 Assumed Known

x1  x2 z / 2  x1  x2
where:
1 -  is the confidence coefficient
 Interval Estimate with 1 and 2 Estimated by s1
and s2 x  x z s 1 2  / 2 x1  x2

s12 s22
where: sx1  x2  
n1 n2

© 2003 South-Western/Thomson Learning™

6
 Example: Par, Inc.

 Interval Estimate of 1 - 2: Large-Sample Case

Par, Inc. is a manufacturer of golf
equipment and has developed a new golf ball
that has been designed to provide “extra
distance.” In a test of driving distance using a
mechanical driving device, a sample of Par golf
balls was compared with a sample of golf balls
made by Rap, Ltd., a competitor.
The sample statistics appear on the next
slide.

© 2003 South-Western/Thomson Learning™

7
 Example: Par, Inc.

 Interval Estimate of 1 - 2: Large-Sample Case

• Sample Statistics
Sample #1 Sample #2
Par, Inc. Rap, Ltd.
Sample Size n1 = 120 balls n2 =
80 balls x1 x2
Mean = 235 yards = 218
yards
Standard Dev. s1 = 15 yards s2 =
20 yards

© 2003 South-Western/Thomson Learning™

8
 Example: Par, Inc.

 Point Estimate of the Difference Between Two

Population Means
1 = mean distance for the population of
Par, Inc. golf balls
2 = mean distance for the population of
Rap, Ltd. golf balls
1  x2
Point estimate of 1 - 2x= = 235 - 218 =
17 yards.

© 2003 South-Western/Thomson Learning™

9
 Point Estimator of the Difference
between the Means of Two Populations

Population 1 Population 2
Par, Inc. Golf Balls Rap, Ltd. Golf Balls
11 = mean driving 22 = mean driving
distance of Par distance of Rap
golf balls golf balls
1 – 2 = difference between
the mean distances
Simple random sample Simple random sample
of n11 Par golf balls of n22 Rap golf balls
x11 = sample mean distance x22 = sample mean distance
for sample of Par golf ball for sample of Rap golf ball
x1 - x2 = Point Estimate of 1 –
2
© 2003 South-Western/Thomson Learning™
10
 Example: Par, Inc.

 95% Confidence Interval Estimate of the Difference

Between Two Population Means: Large-Sample
Case, 1 and 2 Estimated by s1 and s2
Substituting the sample standard deviations
for the population standard deviation:

12  22 (15) 2 ( 20) 2

x1  x2 z / 2  17 1. 96 
n1 n2 120 80
= 17 + 5.14 or 11.86 yards to 22.14 yards.
We are 95% confident that the difference between
the mean driving distances of Par, Inc. balls and
Rap, Ltd. balls lies in the interval of 11.86 to 22.14
yards.

© 2003 South-Western/Thomson Learning™

11
Using Excel to Develop an Interval Estimate
of 1 – 2: Large-Sample Case
 Formula Worksheet
A B C D E
1 Par Rap Par, Inc. Rap, Ltd.
2 195 226 Sample Size 120 80
3 230 198 Mean =AVERAGE(A2:A121) =AVERAGE(A2:A81)
4 254 203 Stand. Dev. =STDEV(A2:A121) =STDEV(A2:A81)
5 205 237
6 260 235 Confid. Coeff. 0.95
7 222 204 Lev. of Signif. =1-D6
8 241 199 z Value =NORMSINV(1-D7/2)
9 217 202
10 228 240 Std. Error =SQRT(D4^2*/D2+E4^2/E2)
11 255 221 Marg. of Error =D8*D10
12 209 206
13 251 201 Pt. Est. of Diff. =D3-E3
14 229 233 Lower Limit =D13-D11
15 220 194 Upper Limit =D13+D11

Note: Rows 16-121 are not shown.

© 2003 South-Western/Thomson Learning™
12
Using Excel to Develop an Interval Estimate
of 1 – 2: Large-Sample Case
 Value Worksheet
A B C D E
1 Par Rap Par, Inc. Rap, Ltd.
2 195 226 Sample Size 120 80
3 230 198 Mean 235 218
4 254 203 Stand. Dev. 15 20
5 205 237
6 260 235 Confid. Coeff. 0.95
7 222 204 Lev. of Signif. 0.05
8 241 199 z Value 1.960
9 217 202
10 228 240 Std. Error 2.622
11 255 221 Marg. of Error 5.139
12 209 206
13 251 201 Pt. Est. of Diff. 17
14 229 233 Lower Limit 11.86
15 220 194 Upper Limit 22.14

Note: Rows 16-121 are not shown.

© 2003 South-Western/Thomson Learning™
13
 Interval Estimate of 1 - 2:
Small-Sample Case (n1 < 30 and/or n2 <
30)
 Interval Estimate with 2 Assumed Known

x1  x2 z / 2  x1  x2
where:
1 1
2
 x1  x2   (  )
n1 n2

© 2003 South-Western/Thomson Learning™

14
 Interval Estimate of 1 - 2:
Small-Sample Case (n1 < 30 and/or n2 <
30)
 Interval Estimate with 1 and 2 Estimated by s1
and s2 x  x t s 1 2  / 2 x1  x2

where: 2 2
2 1 1 ( n  1) s  ( n  1) s
sx1  x2  s (  ) s2  1 1 2 2
n1 n2 n1  n2  2

© 2003 South-Western/Thomson Learning™

15
 Example: Specific Motors

Specific Motors of Detroit has developed a new

automobile known as the M car. 12 M cars and 8 J
cars
(from Japan) were road tested to compare miles-per-
gallon (mpg) performance. The sample statistics are:

Sample #1 Sample
#2
M Cars J Cars
Sample Size xn11 = 12 cars n2x=
2
8 cars
Mean = 29.8 mpg = 27.3
mpg
Standard Deviation s1 = 2.56 mpg s2 = 1.81
mpg
© 2003 South-Western/Thomson Learning™
16
 Example: Specific Motors

 Point Estimate of the Difference Between Two

Population Means

1 = mean miles-per-gallon for the population of

M cars
2 = mean miles-per-gallon for the population of
J cars
1  x2
Point estimate of 1 - 2x= = 29.8 - 27.3
= 2.5 mpg.

© 2003 South-Western/Thomson Learning™

17
 Example: Specific Motors

 95% Confidence Interval Estimate of the Difference

Between Two Population Means: Small-Sample Case
We will make the following assumptions:
• The miles per gallon rating must be normally
distributed for both the M car and the J car.
• The variance in the miles per gallon rating must
be the same for both the M car and the J car.
Using the t distribution with n1 + n2 - 2 = 18 degrees
of freedom, the appropriate t value is t.025 = 2.101.
We will use a weighted average of the two sample
variances as the pooled estimator of 2.

© 2003 South-Western/Thomson Learning™

18
 Example: Specific Motors

 95% Confidence Interval Estimate of the Difference

Between Two Population Means: Small-Sample
Case
2 2 2 22 2 2 2
( n  1) s  ( n  1) s 11( 2. 56)  7 (1. 81)
s2  1 1 2 2
 5. 28
n1  n2  2 12  8  2

21 1 1 1
x1  x2 t.025 s (  ) 2. 5 2.101 5. 28(  )
n1 n2 12 8

= 2.5 + 2.2 or .3 to 4.7 miles per gallon.

We are 95% confident that the difference between
the
mean mpg ratings of the two car types is from 0.3
to 4.7 mpg (with the M car having the higher mpg).

© 2003 South-Western/Thomson Learning™

19
Using Excel to Develop an Interval Estimate
of 1 – 2: Small-Sample Case
 Formula Worksheet
A B C D E
1 M Car J Car M Car J Car
2 25.1 25.6 Sample Size 12 8
3 32.2 28.1 Mean =AVERAGE(A2:A13) =AVERAGE(B2:B9)
4 31.7 27.9 Stand. Dev. =STDEV(A2:A13) =STDEV(B2:B9)
5 27.6 25.3
6 28.5 30.1 Confid. Coeff. 0.95
7 33.6 27.5 Lev. of Signif. =1-D6
8 30.8 25.1 Deg. Freed. =D2+E2-2
9 26.2 28.8 z Value =TINV(D7,D8)
10 29.0
11 31.0 Pool.Est.Var. =((D2-1)*D4^2+(E2-1)*E4^2)/D8
12 31.7 Std. Error =SQRT(D11*(1/D2+1/E2))
13 30.0 Marg. of Error =D9*D12
14
15 Pt. Est. of Diff. =D3-E3
16 Lower Limit =D15-D13
17 Upper Limit =D15+D13
© 2003 South-Western/Thomson Learning™
20
Using Excel to Develop an Interval Estimate
of 1 – 2: Small-Sample Case
 Value Worksheet
A B C D E
1 M Car J Car M Car J Car
2 25.1 25.6 Sample Size 12 8
3 32.2 28.1 Mean 29.8 27.3
4 31.7 27.9 Stand. Dev. 2.56 1.81
5 27.6 25.3
6 28.5 30.1 Confid. Coeff. 0.95
7 33.6 27.5 Lev. of Signif. 0.05
8 30.8 25.1 Deg. Freed. 18
9 26.2 28.8 z Value 2.101
10 29.0
11 31.0 Pool.Est.Var. 5.2765
12 31.7 Std. Error 1.0485
13 30.0 Marg. of Error 2.2027
14
15 Pt. Est. of Diff. 2.4833
16 Lower Limit 0.2806
17 Upper Limit 4.6861
© 2003 South-Western/Thomson Learning™
21
 Hypothesis Tests about the Difference
between the Means of Two Populations:
Independent Samples
 Hypotheses
H0: 1 - 2 < 0 H0: 1 - 2 > 0 H0:
1 - 2 = 0
Ha: 1 - 2 > 0 Ha: 1 - 2 < 0 Ha:
1 - 2  0
 Test Statistic
( x1  x2 )  ( 1   2 ) ( x1  x2 )  ( 1   2 )
z t 
12 n1Large-Sample
  22 n2 s2 (1 n1  1 n2 )
Small-Sample

© 2003 South-Western/Thomson Learning™

22
 Example: Par, Inc.

 Hypothesis Tests About the Difference

Between the Means of Two Populations:
Large-Sample Case
Par, Inc. is a manufacturer of golf equipment
and has developed a new golf ball that has
been designed to provide “extra distance.” In
a test of driving distance using a mechanical
driving device, a sample of Par golf balls was
compared with a sample of golf balls made by
Rap, Ltd., a competitor. The sample statistics
appear on the next slide.

© 2003 South-Western/Thomson Learning™

23
 Example: Par, Inc.

 Hypothesis Tests about the Difference between

the Means of Two Populations: Large-Sample Case
• Sample Statistics
Sample #1 Sample #2
Par, Inc. Rap, Ltd.
Sample Size n1 = 120 balls n2 = 80
balls
x1 x2
Mean = 235 yards = 218
yards
Standard Dev. s1 = 15 yards s2 = 20
yards

© 2003 South-Western/Thomson Learning™

24
 Example: Par, Inc.

 Hypothesis Tests about the Difference between the

Means of Two Populations: Large-Sample Case
Can we conclude, using a .01 level of significance,
that the mean driving distance of Par, Inc. golf balls
is greater than the mean driving distance of Rap,
Ltd. golf balls?
1 = mean distance for the population of Par, Inc.
golf balls
2 = mean distance for the population of Rap, Ltd.
golf balls
• Hypotheses H0: 1 - 2 < 0
Ha: 1 - 2 > 0

© 2003 South-Western/Thomson Learning™

25
 Example: Par, Inc.

 Hypothesis Tests about the Difference

between the Means of Two Populations:
Large-Sample Case
• Rejection Rule Reject H0 if z > 2.33
( x1  x2 )  ( 1   2 ) ( 235  218)  0 17
z   6. 49
2
1  2 2 2
(15) ( 20) 2 2. 62
 
n1 n2 120 80

• Conclusion
Reject H0. We are at least 99%
confident that the mean driving distance
of Par, Inc. golf balls is greater than the mean
driving distance of Rap, Ltd. golf balls.
© 2003 South-Western/Thomson Learning™
26
Using Excel to Conduct a Hypothesis Test
about 1 – 2: Large Sample Case

 Excel’s “z-Test: Two Sample for Means” Tool

Step 1 Select the Tools pull-down menu
Step 2 Choose the Data Analysis option
Step 3 Choose z-Test: Two Sample for
Means
from the list of Analysis Tools

… continued

© 2003 South-Western/Thomson Learning™

27
Using Excel to Conduct a Hypothesis Test
about 1 – 2: Large Sample Case
 Excel’s “z-Test: Two Sample for Means” Tool
Step 4 When the z-Test: Two Sample for Means
dialog box appears:
Enter A1:A121 in the Variable 1 Range
box
Enter B1:B81 in the Variable 2 Range box
Enter 0 in the Hypothesized Mean
Difference box
Enter 225 in the Variable 1 Variance
(known) box
Enter 400 in the Variable 2 Variance
(known) box
… continued
© 2003 South-Western/Thomson Learning™
28
Using Excel to Conduct a Hypothesis Test
about 1 – 2: Large Sample Case
 Excel’s “z-Test: Two Sample for Means” Tool
Step 4 (continued)
Select Labels
Enter .01 in the Alpha box
Select Output Range
Enter D4 in the Output Range box
(Any upper left-hand corner cell
indicating
where the output is to begin may be
entered)
Click OK

© 2003 South-Western/Thomson Learning™

29
 Using Excel to Conduct a Hypothesis Test
about 1 – 2: Large Sample Case
 Value Worksheet
A B C D E F
1 Par Rap Par, Inc. Rap, Ltd.
2 195 226 Sample Variance 225 400
3 230 198
4 254 203 z-Test: Two Sample for Means
5 205 237
6 260 235 Par, Inc. Rap, Ltd.
7 222 204 Mean 235 218
8 241 199 Known Variance 225 400
9 217 202 Observations 120 80
10 228 240 Hypothesized Mean Difference 0
11 255 221 z 6.483545607
12 209 206 P(Z<=z) one-tail 4.50145E-11
13 251 201 z Critical one-tail 2.326341928
14 229 233 P(Z<=z) two-tail 9.00291E-11
15 220 194 z Critical two-tail 2.575834515
Note: Rows 16-121 are not shown.
© 2003 South-Western/Thomson Learning™
30
 Example: Specific Motors

 Hypothesis Tests about the Difference

between the Means of Two Populations: Small-
Sample Case
Can we conclude, using a .05 level of
significance, that the miles-per-gallon (mpg)
performance of M cars is greater than the
miles-per-gallon performance of J cars?
1 = mean mpg for the population of M cars
2 = mean mpg for the population of J cars
• Hypotheses H0: 1 - 2 < 0
Ha: 1 - 2 > 0

© 2003 South-Western/Thomson Learning™

31
 Example: Specific Motors

 Hypothesis Tests about the Difference

between the Means of Two Populations: Small-
Sample Case
• Rejection Rule
Reject H0 if t > 1.734
( = .05, d.f. = 18)
• Test Statistic ( x1  x2 )  ( 1   2 )
t
s2 (1 n1  1 n2 )

2 2
2 (n  1)s  (n  1)s
 1
swhere: 1 2 2

n1  n2  2

© 2003 South-Western/Thomson Learning™

32
Using Excel to Conduct a Hypothesis Test
about 1 – 2: Small Sample Case

 Excel’s “t-Test: Two Sample Assuming Equal

Variances” Tool
Step 1 Select the Tools pull-down menu
Step 2 Choose the Data Analysis option
Step 3 Choose t-Test: Two Sample
Assuming Equal Variances from
the list of Analysis Tools

… continued

© 2003 South-Western/Thomson Learning™

33
Using Excel to Conduct a Hypothesis Test
about 1 – 2: Small Sample Case

 Excel’s “t-Test: Two Sample Assuming Equal

Variances” Tool
Step 4 When the t-Test: Two Sample Assuming
Equal Variances dialog box
appears:
Enter A1:A13 in the Variable 1 Range
box
Enter B1:B9 in the Variable 2 Range
box
Enter 0 in the Hypothesized Mean
Difference box

… continued
© 2003 South-Western/Thomson Learning™
34
Using Excel to Conduct a Hypothesis Test
about 1 – 2: Small Sample Case
 Excel’s “t-Test: Two Sample Assuming Equal
Variances” Tool
Step 4 (continued)
Select Labels
Enter .01 in the Alpha box
Select Output Range
Enter D1 in the Output Range box
(Any upper left-hand corner cell
indicating
where the output is to begin may be
entered)
Click OK

© 2003 South-Western/Thomson Learning™

35
Using Excel to Conduct a Hypothesis Test
about 1 – 2: Small Sample Case
 Value Worksheet
A B C D E F
1 M Car J Car t-Test: Two-Sample Assuming Equal Variances
2 25.1 25.6
3 32.2 28.1 M Car J Car
4 31.7 27.9 Mean 29.78333 27.3
5 27.6 25.3 Variance 6.556061 3.265714
6 28.5 30.1 Observations 12 8
7 33.6 27.5 Pooled Variance 5.276481
8 30.8 25.1 Hypothesized Mean Diff. 0
9 26.2 28.8 df 18
10 29.0 t Stat 2.368555
11 31.0 P(T<=t) one-tail 0.014626
12 31.7 t Critical one-tail 1.734063
13 30.0 P(T<=t) two-tail 0.029251
14 t Critical two-tail 2.100924
© 2003 South-Western/Thomson Learning™
36
 Inference about the Difference between
the Means of Two Populations: Matched
Samples
 With a matched-sample design each sampled
item provides a pair of data values.
 The matched-sample design can be referred to
as blocking.
 This design often leads to a smaller sampling
error than the independent-sample design
because variation between sampled items is
eliminated as a source of sampling error.

© 2003 South-Western/Thomson Learning™

37
 Example: Express Deliveries

 Inference about the Difference between the

Means of Two Populations: Matched Samples
A Chicago-based firm has documents that
must be quickly distributed to district offices
throughout the U.S. The firm must decide
between two delivery services, UPX (United
Parcel Express) and INTEX (International
Express), to transport its documents. In testing
the delivery times of the two services, the firm
sent two reports to a random sample of ten
district offices with one report carried by UPX
and the other report carried by INTEX.
Do the data that follow indicate a
difference in mean delivery times for the two
services?
© 2003 South-Western/Thomson Learning™
38
 Example: Express Deliveries

Delivery Time (Hours)

District Office UPX INTEX Difference
Seattle 32 25 7
Los Angeles 30 24 6
Boston 19 15 4
Cleveland 16 15 1
New York 15 13 2
Houston 18 15 3
Atlanta 14 15 -1
St. Louis 10 8 2
Milwaukee 7 9 -2
Denver 16 11 5

© 2003 South-Western/Thomson Learning™

39
 Example: Express Deliveries

 Inference about the Difference between the Means

of Two Populations: Matched Samples
Let d = the mean of the difference values for
the two delivery services for the
population of district offices

• Hypotheses H0: d = 0, Ha: d 

• Rejection Rule
Assuming the population of difference values
is approximately normally distributed, the t
distribution with n - 1 degrees of freedom
applies. With  = .05, t.025 = 2.262 (9 degrees of
freedom).
Reject H0 if t < -2.262 or if t > 2.262
© 2003 South-Western/Thomson Learning™
40
 Example: Express Deliveries

 Inference about the Difference between the

Means of Two Populations: Matched Samples
 di ( 7  6... 5)
d   2. 7
n 10
2
 ( di  d ) 76.1
sd   2. 9
n 1 9
d  d 2. 7  0
t  2. 94
sd n 2. 9 10

• Conclusion Reject H0.

There is a significant difference between the
mean delivery times for the two services.
© 2003 South-Western/Thomson Learning™
41
Using Excel to Conduct a Hypothesis Test
about 1 – 2: Matched Samples

 Excel’s “t-Test: Paired Two Sample for Means”

Tool
Step 1 Select the Tools pull-down menu
Step 2 Choose the Data Analysis option
Step 3 Choose t-Test: Paired Two Sample
for Means
from the list of Analysis Tools

… continued

© 2003 South-Western/Thomson Learning™

42
Using Excel to Conduct a Hypothesis Test
about 1 – 2: Matched Samples
 Excel’s “t-Test: Paired Two Sample for Means” Tool
Step 4 When the t-Test: Paired Two Sample for Means
dialog box appears:
Enter B1:B11 in the Variable 1 Range box
Enter C1:C11 in the Variable 2 Range box
Enter 0 in the Hypothesized Mean
Difference box
Select Labels
Enter .05 in the Alpha box
Select Output Range
Enter E2 (your choice) in the Output
Range box
Click OK

© 2003 South-Western/Thomson Learning™

43
Using Excel to Conduct a Hypothesis Test
about 1 – 2: Matched Samples
 Value Worksheet
A B C D E F G
1 Office UPX INTEX
2 Seattle 32 25 t-Test: Paired Two Sample for Means
3 L.A. 30 24
4 Boston 19 15 UPX INTEX
5 Cleveland 16 15 Mean 17.7 15
6 N.Y.C. 15 13 Variance 62.011 31.7778
7 Houston 18 15 Observations 10 10
8 Atlanta 14 15 Pearson Correlation 0.9612
9 St. Louis 10 8 Hypothesized Mean Difference 0
10 Milwauk. 7 9 df 9
11 Denver 16 11 t Stat 2.9362
12 P(T<=t) one-tail 0.0083
13 t Critical one-tail 1.8331
14 P(T<=t) two-tail 0.0166
15 t Critical two-tail 2.2622
© 2003 South-Western/Thomson Learning™
44
 Inferences about the Difference between
the Proportions of Two Populations
 Sampling Distribution of
p1  p2
 Interval Estimation of p1 - p2
 Hypothesis Tests about p1 - p2

© 2003 South-Western/Thomson Learning™

45
 Sampling Distribution of p1  p2

 Expected Value
E ( p1  p2 )  p1  p2
 Standard Deviation

p1 (1  p1 ) p2 (1  p2 )
 p1  p2  
n1 n2
 Distribution Form
If the sample sizes are large (n1p1, n1(1 - p1),
n2p2,
and n2(1 - p2) are all greater than or equal to 5), the
sampling distribution of p1  p2 can be approximated
by a normal probability distribution.

© 2003 South-Western/Thomson Learning™

46
 Interval Estimation of p1 - p2

 Interval Estimate
p1  p2 z / 2  p1  p2

  p1  p2
Point Estimator of

p1 (1  p1 ) p2 (1  p2 )
s p1  p2  
n1 n2

© 2003 South-Western/Thomson Learning™

47
 Example: MRA

MRA (Market Research Associates) is

conducting research to evaluate the
effectiveness of a client’s new advertising
campaign. Before the new campaign began, a
telephone survey of 150 households in the test
market area showed 60 households “aware” of
the client’s product. The new campaign has been
initiated with TV and newspaper advertisements
running for three weeks. A survey conducted
immediately after the new campaign showed 120
of 250 households “aware” of the client’s
product.
Does the data support the position that the
advertising campaign has provided an increased
awareness of the client’s product?
© 2003 South-Western/Thomson Learning™
48
 Example: MRA

 Point Estimator of the Difference between the

Proportions of Two Populations
120 60
p1  p2  p1  p2   . 48 . 40 . 08
250 150
p1 = proportion of the population of households
“aware” of the product after the new
campaign
p2 = proportion of the population of households
“aware” of the product before the new
campaign
p1 = sample proportion of households “aware” of the
product after the new campaign
p2 = sample proportion of households “aware” of the
product before the new campaign

© 2003 South-Western/Thomson Learning™

49
 Example: MRA

 Interval Estimate of p1 - p2: Large-Sample Case

For = .05, z.025 = 1.96:
. 48(. 52) . 40(. 60)
. 48 . 40 1. 96 
250 150
.08 + 1.96(.0510)
.08 + .10
or -.02 to +.18
• Conclusion
At a 95% confidence level, the interval
estimate of the difference between the proportion
of households aware of the client’s product before
and after the new advertising campaign is -.02 to
+.18.
© 2003 South-Western/Thomson Learning™
50
 Using Excel to Develop
an Interval Estimate of p1 – p2
 Formula Worksheet
A B C D E
1 Sur2 Sur1 Survey 2 (from Popul.1) Survey 1 (from Popul.2)
2 No Yes Sample Size 250 150
3 Yes No No. of "Yes" =COUNTIF(A2:A251,"Yes") =COUNTIF(B2:B151,"Yes")
4 Yes Yes Samp. Propor. =D3/D2 =E3/E2
5 No Yes
6 Yes No Confid. Coeff. 0.95
7 No No Lev. Of Signif. =1-D6
8 No Yes z Value =NORMSINV(1-D7/2)
9 Yes No
10 No No Std. Error =SQRT(D4*(1-D4)/D2+E4*(1-E4)/E2)
11 Yes Yes Marg. of Error =D8*D10
12 Yes No
13 Yes Yes Pt. Est. of Diff. =D4-E4
14 No Yes Lower Limit =D13-D11
15 Yes Yes Upper Limit =D13+D11

Note: Rows 16-251 are not shown.

© 2003 South-Western/Thomson Learning™

51
 Using Excel to Develop
an Interval Estimate of p1 – p2
 Value Worksheet
A B C D E
1 Sur2 Sur1 Survey 2 (from Popul.1) Survey 1 (from Popul.2)
2 No Yes Sample Size 250 150
3 Yes No No. of "Yes" 120 60
4 Yes Yes Samp. Propor. 0.48 0.40
5 No Yes
6 Yes No Confid. Coeff. 0.95
7 No No Lev. Of Signif. 0.05
8 No Yes z Value 1.960
9 Yes No
10 No No Std. Error 0.0510
11 Yes Yes Marg. of Error 0.0999
12 Yes No
13 Yes Yes Pt. Est. of Diff. 0.080
14 No Yes Lower Limit -0.020
15 Yes Yes Upper Limit 0.180

Note: Rows 16-251 are not shown.

© 2003 South-Western/Thomson Learning™

52
 Hypothesis Tests about p1 - p2

 Hypotheses
H0: p1 - p2 < 0
Ha: p1 - p2 > 0
 Test statistic
( p  p2 )  ( p1  p2 )
z 1
 p1  p2

 Point Estimator of  p1  p2 where p1 = p2

s p1  p2  p (1  p )(1 n1  1 n2 )
n p n p
p 1 1 2 2
where: n1  n2

© 2003 South-Western/Thomson Learning™

53
 Example: MRA

 Hypothesis Tests about p1 - p2

Can we conclude, using a .05 level of
significance, that the proportion of households
aware of the client’s product increased after the
new advertising campaign?
p1 = proportion of the population of households
“aware” of the product after the new
campaign
p2 = proportion of the population of households
“aware” of the product before the new
campaign
• Hypotheses H0: p1 - p2 < 0
H a: p 1 - p 2 > 0
© 2003 South-Western/Thomson Learning™
54
 Example: MRA

 Hypothesis Tests about p1 - p2

• Rejection Rule Reject H0 if z > 1.645
• Test Statistic
250(. 48)  150(. 40) 180
p  . 45
250  150 400

s p1  p2  . 45(. 55)( 1  1 ) . 0514

250 150

(. 48 . 40)  0 . 08
z  1. 56
. 0514 . 0514

• Conclusion Do not reject H0.

© 2003 South-Western/Thomson Learning™

55
 Using Excel to Conduct
a Hypothesis Test about p1 – p2
 Formula Worksheet
A B C D E
1 Sur2 Sur1 Survey 2 (from Popul.1) Survey 1 (from Popul.2)
2 No Yes Sample Size 250 150
3 Yes No No. of "Yes" =COUNTIF(A2:A251,"Yes") =COUNTIF(B2:B151,"Yes")
4 Yes Yes Samp. Propor. =D3/D2 =E3/E2
5 No Yes
6 Yes No Lev of Signif. 0.05
7 No No Crit.Val. (upper) =NORMSINV(1-D7)
8 No Yes
9 Yes No Pt. Est. of Diff. =D4-E4
10 No No Hypoth. Value 0
11 Yes Yes
12 Yes No Pool. Est. of p =(D2*D4+E2*E4)/(D2+E2)
13 Yes Yes Standard Error =SQRT(D12*(1-D12)*(1/D2+1/E2))
14 No Yes Test Statistic =(D9-D10)/D13
15 Yes Yes p -Value =2*NORMSDIST(D14)
16 Yes No Conclusion =IF(D15<D6,"Reject","Do Not Reject")
Note: Rows 17-251 are not shown.
© 2003 South-Western/Thomson Learning™
56
 Using Excel to Conduct
a Hypothesis Test about p1 – p2
 Value Worksheet
A B C D E
1 Sur2 Sur1 Survey 2 (from Popul.1) Survey 1 (from Popul.2)
2 No Yes Sample Size 250 150
3 Yes No No. of "Yes" 120 60
4 Yes Yes Samp. Propor. 0.48 0.40
5 No Yes
6 Yes No Lev of Signif. 0.05
7 No No Crit.Val. (upper) 1.645
8 No Yes
9 Yes No Pt. Est. of Diff. 0.08
10 No No Hypoth. Value 0
11 Yes Yes
12 Yes No Pool. Est. of p 0.450
13 Yes Yes Standard Error 0.0514
14 No Yes Test Statistic 1.557
15 Yes Yes p -Value 0.060
16 Yes No Conclusion Do Not Reject

Note: Rows 17-251 are not shown.

© 2003 South-Western/Thomson Learning™
57
 End of Chapter 10

© 2003 South-Western/Thomson Learning™

58