Slides Prepared by

JOHN S. LOUCKS
St. Edward’s University

© 2003 South-Western /Thomson Learning™

1
 Chapter 11
Inferences about Population Variances
 Inference about a Population Variance
 Inferences about the Variances of Two
Populations

© 2003 South-Western /Thomson Learning™

2
 Inferences about a Population Variance

 Chi-Square Distribution
 Interval Estimation of 2
 Hypothesis Testing

© 2003 South-Western /Thomson Learning™

3
 Chi-Square Distribution

 The chi-square distribution is the sum of squared

standardized normal random variables such as
(z1)2+(z2)2+(z3)2 and so on.
 The chi-square distribution is based on sampling
from a normal population.
 The sampling distribution of (n - 1)s2/2 has a
chi-square distribution whenever a simple
random sample of size n is selected from a
normal population.
 We can use the chi-square distribution to
develop interval estimates and conduct
hypothesis tests about a population variance.

© 2003 South-Western /Thomson Learning™

4
 Interval Estimation of 2

 Interval Estimate of a Population Variance

( n  1) s 2 2 ( n  1) s 2
2
 
 /2  2(1  / 2 )

where the values are based on a chi-square

distribution with n - 1 degrees of freedom and
where 1 -  is the confidence coefficient.

© 2003 South-Western /Thomson Learning™

5
 Interval Estimation of 

 Interval Estimate of a Population Standard

Deviation
Taking the square root of the upper and
lower limits of the variance interval provides
the confidence interval for the population
standard deviation.

© 2003 South-Western /Thomson Learning™

6
 Interval Estimation of 2

 Chi-Square Distribution With Tail Areas of .025

.025
.025
95% of the
possible 2 values
2
2 2
0  .975  .025

© 2003 South-Western /Thomson Learning™

7
 Example: Buyer’s Digest (A)

Buyer’s Digest rates thermostats manufactured

for home temperature control. In a recent test, 10
thermostats manufactured by ThermoRite were
selected
and placed in a test room that was maintained at a
temperature of 68oF. The temperature readings of the
ten thermostats are listed below.
We will use the 10 readings to develop a 95%
confidence interval estimate of the population variance.

Therm. 1 2 3 4 5 6 7 8
9 10
Temp. 67.4 67.8 68.2 69.3 69.5 67.0 68.1 68.6
67.9 67.2
© 2003 South-Western /Thomson Learning™
8
 Example: Buyer’s Digest (A)

 Interval Estimation of 2

n - 1 = 10 - 1 = 9 degrees of freedom and 
= .05 2
(n  1)s
 2
.975    2
.025
 2

.025
.025

2
0 
2
.975
 .025
2

© 2003 South-Western /Thomson Learning™

9
 Example: Buyer’s Digest (A)

 Interval Estimation of 2

n - 1 = 10 - 1 = 9 degrees of freedom and 
= .05
(n  1)s2
2.70    2
.025
2


.025
Area in
Upper Tail
= .975
2
0 2.70

© 2003 South-Western /Thomson Learning™

10
 Example: Buyer’s Digest (A)

 Interval Estimation of 2

n - 1 = 10 - 1 = 9 degrees of freedom and 
= .05 2
( n  1) s
2. 70  2
19 . 02


.025 Area in Upper

Tail = .025

2
0 2.70 19.02

© 2003 South-Western /Thomson Learning™

11
 Example: Buyer’s Digest (A)

 Interval Estimation of 2

Sample variance s2 provides a point estimate of
2. 2
2  ( x i  x ) 6. 3
s   . 70
n 1 9

A 95% confidence interval for the population

(10  by:
variance is given 1). 70 2 (10  1). 70
 
19 . 02 2 . 70

.33 < 2 < 2.33

© 2003 South-Western /Thomson Learning™

12
 Using Excel to Construct an Interval
Estimate
of a Population Variance
 Formula Worksheet
A B C
1 Temp. Sample Size =COUNT(A2:A11)
2 67.4 Variance =VAR(A2:A11)
3 67.8
4 68.2 Confid. Coefficient 0.95
5 69.3 Level of Signif. (alpha) =1-C4
6 69.5 Chi-Sq. Value (low. tail) =CHIINV(1-C5/2,C1-1)
7 67.0 Chi-Sq. Value (up. tail) =CHIINV(C5/2,C1-1)
8 68.1
9 68.6 Point Estimate =C2
10 67.9 Lower Limit =((C1-1)*C2)/C7
11 67.2 Upper Limit =((C1-1)*C2)/C6

© 2003 South-Western /Thomson Learning™

13
 Using Excel to Construct an Interval
Estimate
of a Population Variance
 Value Worksheet
A B C
1 Temp. Sample Size 10
2 67.4 Variance 0.700
3 67.8
4 68.2 Confid. Coefficient 0.95
5 69.3 Level of Signif. (alpha) 0.05
6 69.5 Chi-Sq. Value (low. tail) 2.700
7 67.0 Chi-Sq. Value (up. tail) 19.023
8 68.1
9 68.6 Point Estimate 0.700
10 67.9 Lower Limit 0.331
11 67.2 Upper Limit 2.333

© 2003 South-Western /Thomson Learning™

14
 Hypothesis Testing about a Population
Variance
 Right-Tailed Test
• Hypotheses
H 0 :  2   20
H a :  2   20
2
0
where is the hypothesized value
for the population variance

• Test Statistic
2 ( n  1) s 2
 
 20

© 2003 South-Western /Thomson Learning™

15
 Hypothesis Testing about a Population
Variance
 Right-Tailed Test (continued)
• Rejection Rule
2 2
Reject H0 if    
Using test statistic:

Reject H0 if p-value < 

Using p-value:


where
2
is based on a chi-square
distribution with n - 1 d.f.

© 2003 South-Western /Thomson Learning™

16
 Hypothesis Testing about a Population
Variance
 Left-Tailed Test
• Hypotheses
H 0 :  2  02
H a :  2   02
2
0
where is the hypothesized value
for the population variance

• Test Statistic
2 ( n  1) s 2
 
 20

© 2003 South-Western /Thomson Learning™

17
 Hypothesis Testing about a Population
Variance
 Left-Tailed Test (continued)
• Rejection Rule
2 2

Reject H0 if
Using test statistic:   (1  )

Reject H0 if p-value < 

Using p-value:

 2
where(1  ) is based on a chi-square
distribution with n - 1 d.f.

© 2003 South-Western /Thomson Learning™

18
 Hypothesis Testing about a Population
Variance
 Two-Tailed Test
• Hypotheses
H 0 :  2   20
H a :  2   20
• Test Statistic
( n  1) s 2
2 
 20

© 2003 South-Western /Thomson Learning™

19
 Hypothesis Testing about a Population
Variance
 Two-Tailed Test (continued)
• Rejection Rule
Using test statistic:
2 2 2 2
RejectH0if (1  / 2) or    / 2

Using p-value:
Reject H0 if p-value < 
(12   / 2) and 2/ 2
where are based
on a
chi-square distribution with n - 1
© 2003 South-Western /Thomson Learning™
d.f. 20
 Example: Buyer’s Digest (B)

Buyer’s Digest is rating ThermoRite thermostats

made for home temperature control. Buyer’s Digest
gives an “acceptable” rating to a thermostat with a
temperature variance of 0.5 or less. In a recent test, 10
ThermoRite thermostats were selected and placed in a
test room that was maintained at a temperature of 68oF.
The temperature readings of the thermostats are listed
below.
Using the 10 readings, we will conduct a hypothesis
test (with  = .05) to determine whether the ThermoRite
thermostat’s temperature variance is “acceptable”.

Therm. 1 2 3 4 5 6 7 8 9
10
Temp. 67.4 67.8 68.2 69.3 69.5 67.0 68.1 68.6 67.9
67.2
© 2003 South-Western /Thomson Learning™
21
 Example: Buyer’s Digest (B)

 Hypotheses
H 0 :  2 0.5
H a :  2  0.5

 Rejection Rule
Reject H0 if 2 > 14.6837

© 2003 South-Western /Thomson Learning™

22
 Example: Buyer’s Digest (B)

 Rejection Region
2
(n  1)s 9s2
 
2

 2
.5

.10

2
0 14.6837
Reject H00

© 2003 South-Western /Thomson Learning™

23
 Example: Buyer’s Digest (B)

 Test Statistic
The sample variance s2 = 0.7
29(.7)
  12.6
.5
 Conclusion
Because 2 = 12.6 is less than 14.6837, we
cannot reject H0. The sample variance s2 = .7
is insufficient evidence to conclude that the
temperature variance for ThermoRite
thermostats is unacceptable.

© 2003 South-Western /Thomson Learning™

24
 Using Excel to Conduct a Hypothesis Test
about a Population Variance
 Formula Worksheet
A B C
1 Temp. Sample Size =COUNT(A2:A11)
2 67.4 Variance =VAR(A2:A11)
3 67.8
4 68.2 Hypothesized Value 0.5
5 69.3
6 69.5 Test Statistic =((C1-1)*C2)/C4
7 67.0 Degrees of Freedom =C1-1
8 68.1
9 68.6 p -Value (Lower Tail) =1-CHIDIST(C6,C7)
10 67.9 p -Value (Upper Tail) =CHIDIST(C6,C7)
11 67.2 p -Value (Two Tail) =2*MIN(C9,C10)

© 2003 South-Western /Thomson Learning™

25
 Using Excel to Conduct a Hypothesis Test
about a Population Variance
 Value Worksheet
A B C
1 Temp. Sample Size 10
2 67.4 Variance 0.7
3 67.8
4 68.2 Hypothesized Value 0.5
5 69.3
6 69.5 Test Statistic 12.6
7 67.0 Degrees of Freedom 9
8 68.1
9 68.6 p -Value (Lower Tail) 0.818443367
10 67.9 p -Value (Upper Tail) 0.181556633
11 67.2 p -Value (Two Tail) 0.363113265

© 2003 South-Western /Thomson Learning™

26
 Using Excel to Conduct a Hypothesis Test
about a Population Variance
 Using the p-Value
• The rejection region for the ThermoRite
thermostat example is in the upper tail;
thus, the appropriate p-value is .1816.
• Because .1816 >  = .10, we cannot reject
the null hypothesis.
• The sample variance of s2 = .7 is insufficient
evidence to conclude that the temperature
variance is unacceptable (>.5)

© 2003 South-Western /Thomson Learning™

27
 Hypothesis Testing about the Variances
of Two Populations
 One-Tailed Test
• Hypotheses
H 0 :  12  22
H a :  12   22

Denote the population providing the

larger sample variance as population
1.
• Test Statistic s12
F
s22

© 2003 South-Western /Thomson Learning™

28
 Hypothesis Testing about the Variances
of Two Populations
 One-Tailed Test (continued)
• Rejection Rule
Reject H0 if F > F
Using test statistic:

where the value of F is based on an F

distribution with n1 - 1 (numerator) and
n2 - 1 (denominator) d.f.
Reject H0 if p-value < 
Using p-value:

© 2003 South-Western /Thomson Learning™

29
 Hypothesis Testing about the Variances
of Two Populations
 Two-Tailed Test
• Hypotheses
H 0 :  12   22
H a :  12   22

Denote the population providing the

larger sample variance as population
1.
• Test Statistic s12
F
s22

© 2003 South-Western /Thomson Learning™

30
 Hypothesis Testing about the Variances
of Two Populations
 Two-Tailed Test (continued)
• Rejection Rule
Reject H0 if F > F/2
Using test statistic:

where the value of F/2 is based on an F

distribution with n1 - 1 (numerator) and
n2 - 1 (denominator) d.f.
Reject H0 if p-value < 
Using p-value:

© 2003 South-Western /Thomson Learning™

31
 Example: Buyer’s Digest (C)

Buyer’s Digest has conducted the same test, as was

described earlier, on another 10 thermostats, this time
manufactured by TempKing. The temperature readings
of the ten thermostats are listed below.
We will conduct a hypothesis test with  = .10 to see
if the variances are equal for ThermoRite’s thermostats
and TempKing’s thermostats.

Therm. 1 2 3 4 5 6 7 8 9 10
Temp. 66.467.868.270.3 69.5 68.0 68.1 68.6 67.9
66.2

© 2003 South-Western /Thomson Learning™

32
 Example: Buyer’s Digest (C)

 Hypothesis Testing about the Variances of Two

Populations
• Hypotheses
(TempKing and ThermoRite
H 0 :  12   22
thermo- stats have same
temperature variance)
H a :  12   22 (Their variances are not equal)
• Rejection Rule
The F distribution table shows that with 
= .10,
9 d.f. (numerator), and 9 d.f. (denominator),
F.05 = 3.18.
Reject H0 if F > 3.18

© 2003 South-Western /Thomson Learning™

33
 Example: Buyer’s Digest (C)

 Hypothesis Testing about the Variances of Two

Populations
• Test Statistic
TempKing’s sample variance is 1.52.
ThermoRite’s sample variance is .70.
2
s
F 1 = 1.52/.70 = 2.17
2
s
2

• Conclusion
We cannot reject H0. There is
insufficient
evidence to conclude that the population
variances differ for the two thermostat
brands.
© 2003 South-Western /Thomson Learning™
34
 Using Excel to Conduct a Hypothesis Test
about the Variances of Two Populations
 Excel’s F-Test Two-Sample for Variances Tool
Step 1: Select the Tools pull-down menu
Step 2: Choose the Data Analysis option
Step 3: When the Data Analysis dialog box
appears:
Choose F-Test Two Sample for
Variances
Click OK
… continue

© 2003 South-Western /Thomson Learning™

35
 Using Excel to Conduct a Hypothesis Test
about the Variances of Two Populations
 Excel’s F-Test Two-Sample for Variances Tool
Step 4: When the F-Test Two-Sample for
Variances dialog box appears:
Enter A1:A11 in the Variable 1
Range box
Enter B1:B11 in the Variable 2
Range box
Select Labels
Enter .05 in the Alpha box
Select Output Range
Enter C1 in the Output Range box

© 2003 South-Western /Thomson Learning™

36
 Using Excel to Conduct a Hypothesis Test
about the Variances of Two Populations
 Value Worksheet
A B C D E
Temp- Therm-
1 King oRite F-Test Two-Sample for Variances
2 66.4 67.4
3 67.8 67.8 Temp-King Therm-oRite
4 68.2 68.2 Mean 68.1 68.1
5 70.3 69.3 Variance 1.5222 0.7000
6 69.5 69.5 Observations 10 10
7 68.0 67.0 df 9 9
8 68.1 68.1 F 2.1746
9 68.6 68.6 P(F<=f) one-tail 0.1314
10 67.9 67.9 F Critical one-tail 3.1789
11 66.2 67.2

© 2003 South-Western /Thomson Learning™

37
 Using Excel to Conduct a Hypothesis Test
about the Variances of Two Populations
 Determining and Using the p-Value
• The output labeled P(F<=f) one-tail, 0.1314,
can be used to determine the p-value for the
hypothesis test.
• If the thermostat example had been a one-
tailed hypothesis test, this would have been
the p-value.
• Because the thermostat example is a two-
tailed test, we must multiply the 0.1314 value
by 2 to obtain the correct p-value, 0.2628.
• Because .2628 >  = .10, we cannot reject
the null hypothesis.

© 2003 South-Western /Thomson Learning™

38
 End of Chapter 11

© 2003 South-Western /Thomson Learning™

39