Inferences About Population Variances

ISI:

Inference about a Population Variance

Inferences about the Variances of Two Populations

Inferences About a Population Variance

Chi-Square Distribution
Interval Estimation of 2
Hypothesis Testing

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

Examples of Sampling Distribution of (n 1)s2/2

With 2 degrees
of freedom
With 5 degrees
of freedom
With 10 degrees
of freedom

(n 1) s 2
2

Chi-Square Distribution

We will use the notation

to denote the value
for the chi-square distribution that provides an
2
area of to the right ofthe stated
value.
2

For example, there is a .95 probability of

obtaining a 2 (chi-square) value such that
2
2
.975
2 .025

Interval Estimation of 2
2
(
n

1)
s
2
2
.975

.025
2

.025

.025

95% of the
possible 2 values
2
0 .975

2
.025

Interval Estimation of 2

There is a (1 ) probability of obtaining a 2 value

such that
2
2
2

(1 / 2) / 2

Substituting (n 1)s2/2 for the 2 we get

2
(
n

1)
s
2
(12 / 2)

/2
2

Performing algebraic manipulation we get

2
( n 1) s2
(
n

1
)
s
2

2
2
/2
(1 / 2)

Interval Estimation of 2

Interval Estimate of a Population Variance

2
( n 1) s2
(
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.

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 confidenc
interval for the population standard deviation.

(n 1) s 2
(n 1) s 2

2
/ 2
(12 / 2)

Interval Estimation of 2

Example: Buyers Digest (A)

Buyers 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
shown on the next slide.

Interval Estimation of 2

Example: Buyers Digest (A)

We will use the 10 readings below to

develop a 95% confidence interval
estimate of the population variance.

Thermostat

Temperature 67.4 67.8 68.2 69.3 69.5 67.0 68.1 68.6 6

Interval Estimation of 2
For n - 1 = 10 - 1 = 9 d.f. and = .05

Selected Values from the Chi-Square Distribution Table

Degrees

5
6
7
8
9

.99
0.554
0.872
1.239
1.647
2.088

10

2.558 3.247 3.940 4.865 15.987 18.307 20.483 23.209

of Freedom

.975
0.831
1.237
1.690
2.180
2.700

Area in Upper Tail

.95
.90
.10
.05
1.145
1.635
2.167
2.733
3.325

1.610
2.204
2.833
3.490
4.168

Our 2
.975
value

9.236
10.645
12.017
13.362
14.684

11.070
12.592
14.067
15.507
16.919

.025
12.832
14.449
16.013
17.535
19.023

.01
15.086
16.812
18.475
20.090
21.666

Interval Estimation of 2
For n - 1 = 10 - 1 = 9 d.f. and = .05

(n 1)s2
2
2.700

.025
2
.025

Area in
Upper Tail
= .975
2

0 2.700

Interval Estimation of 2
For n - 1 = 10 - 1 = 9 d.f. and = .05

Selected Values from the Chi-Square Distribution Table

Degrees

5
6
7
8
9

.99
0.554
0.872
1.239
1.647
2.088

10

2.558 3.247 3.940 4.865 15.987 18.307 20.483 23.209

of Freedom

.975
0.831
1.237
1.690
2.180
2.700

Area in Upper Tail

.95
.90
.10
.05
1.145
1.635
2.167
2.733
3.325

1.610
2.204
2.833
3.490
4.168

Our 2
.025
value

9.236
10.645
12.017
13.362
14.684

11.070
12.592
14.067
15.507
16.919

.025
12.832
14.449
16.013
17.535
19.023

.01
15.086
16.812
18.475
20.090
21.666

Interval Estimation of 2
n - 1 = 10 - 1 = 9 degrees of freedom and = .05

(n 1)s2
2.700
19.023
2

.025

Area in Upper
Tail = .025
2

0 2.700

19.023

Interval Estimation of 2

Sample variance s2 provides a point estimate of 2.

2
(
x

x
)
6. 3

i
s2

. 70
n 1
9

A 95% confidence interval for the population

variance is given by:
(10 1). 70
(10 1). 70
2
19. 02
2. 70
.33 < 2 < 2.33

Hypothesis Testing
About a Population Variance

Left-Tailed Test
Hypotheses

H 0 : 2 02
H a : 2 02

where 02 is the hypothesized value

for the population variance
2

Test Statistic

2
(
n

1
)
s
2
20

Hypothesis Testing
About a Population Variance

Left-Tailed Test (continued)

Rejection Rule
2
2
Critical value approach:
Reject H0 if (1 )
p-Value approach: Reject H0 if p-value <
2
where (1
is based on a chi-square
)
distribution with n - 1 d.f.

Hypothesis Testing
About a Population Variance

Right-Tailed Test
Hypotheses

H0 : 2 20
Ha : 2 20

where 02 is the hypothesized value

for the population variance
2

Test Statistic

2
(
n

1
)
s
2
20

Hypothesis Testing
About a Population Variance

Right-Tailed Test (continued)

Rejection Rule
Critical value approach:Reject H0 if 2 2
p-Value approach:Reject H0 if p-value <
2

where is based on a chi-square

distribution with n - 1 d.f.

Hypothesis Testing
About a Population Variance

Two-Tailed Test
Hypotheses

H0 : 2 20
Ha : 2 20

where 02 is the hypothesized value

for the population variance
2

Test Statistic

2
(
n

1
)
s
2
20

Hypothesis Testing
About a Population Variance

Two-Tailed Test (continued)

Rejection Rule
Critical value approach:
Reject H0 if 2 (12 / 2) or 2 2/ 2
p-Value approach:
Reject H0 if p-value <
where (12 / 2) and 2/ 2
are based on a
chi-square distribution with n - 1 d.f.

Hypothesis Testing
About a Population Variance
Example: Buyers Digest (B)
Recall that Buyers Digest is rating
ThermoRite thermostats. Buyers Digest
gives an acceptable rating to a thermostat with a temperature variance of 0.5
or less.

We will conduct a hypothesis test (with

= .10) to determine whether the ThermoRite
thermostats temperature variance is acceptable.

Hypothesis Testing
About a Population Variance
Example: Buyers Digest (B)
Using the 10 readings, we will
conduct a hypothesis test (with = .10)
to determine whether the ThermoRite
thermostats temperature variance is
acceptable.

Thermostat

Temperature 67.4 67.8 68.2 69.3 69.5 67.0 68.1 68.6 6

Hypothesis Testing
About a Population Variance

Hypotheses
H 0 : 2 0.5

H a : 2 0.5

Rejection Rule
Reject H0 if 2 > 14.684

Hypothesis Testing
About a Population Variance
For n - 1 = 10 - 1 = 9 d.f. and = .10

Selected Values from the Chi-Square Distribution Table

Degrees

5
6
7
8
9

.99
0.554
0.872
1.239
1.647
2.088

10

2.558 3.247 3.940 4.865 15.987 18.307 20.483 23.209

of Freedom

.975
0.831
1.237
1.690
2.180
2.700

Area in Upper Tail

.95
.90
.10
.05

Our 2
.10
value

1.145
1.635
2.167
2.733
3.325

1.610
2.204
2.833
3.490
4.168

9.236
10.645
12.017
13.362
14.684

11.070
12.592
14.067
15.507
16.919

.025
12.832
14.449
16.013
17.535
19.023

.01
15.086
16.812
18.475
20.090
21.666

Hypothesis Testing
About a Population Variance

Rejection Region
2
2
(
n

1)
s
9
s
2

.5

Area in Upper
Tail = .10

14.684

2
Reject H0

Hypothesis Testing
About a Population Variance

Test Statistic
The sample variance s 2 = 0.7
9(.7)

12.6
.5
2

Conclusion
Because 2 = 12.6 is less than 14.684, we cannot
reject H0. The sample variance s2 = .7 is insufficient

evidence to conclude that the temperature variance

for ThermoRite thermostats is unacceptable.

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 less than .90 (2 = 4.168)
and greater than .10 (2 = 14.684).
Because the p value > = .10, we cannot
reject the null hypothesis.

The sample variance of s 2 = .7 is insufficient

evidence to conclude that the temperature
variance is unacceptable (>.5).

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

Hypothesis Testing About the

Variances of Two Populations

One-Tailed Test (continued)

Rejection Rule
Critical value approach:
Reject H0 if F > F
where the value of F is based on an
F distribution with n1 - 1 (numerator)
and n2 - 1 (denominator) d.f.
p-Value approach:Reject H0 if p-value <

Hypothesis Testing About the

Variances of Two Populations

Two-Tailed Test
Hypotheses

H0 : 12 22
Ha : 12 22

Denote the population providing the

larger sample variance as population 1.

Test Statistic

s12
F

s22

Hypothesis Testing About the

Variances of Two Populations

Two-Tailed Test (continued)

Rejection Rule
Critical value approach:Reject H0 if F > F/2
where the value of F/2 is based on an
F distribution with n1 - 1 (numerator)
and n2 - 1 (denominator) d.f.
p-Value approach:Reject H0 if p-value <

Hypothesis Testing About the

Variances of Two Populations

Example: Buyers Digest (C)

Buyers 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 on the next slide.
We will conduct a hypothesis test with = .
10 to see
if the variances are equal for ThermoRites
thermostats
and TempKings thermostats.

Hypothesis Testing About the

Variances of Two Populations

Example: Buyers Digest (C)

ThermoRite Sample

Thermostat

Temperature 67.4 67.8 68.2 69.3 69.5 67.0 68.1 68.6 6

TempKing Sample
Thermostat

Temperature 67.7 66.4 69.2 70.1 69.5 69.7 68.1 66.6 6

Hypothesis Testing About the

Variances of Two Populations

Hypotheses

H0 : 12 22

(TempKing and ThermoRite thermostat

have the same temperature variance)

Ha : 12 22

(Their variances are not equal)

Rejection Rule
The F distribution table (on next slide) shows
that with
with = .10, 9 d.f. (numerator), and 9 d.f.
(denominator),
Reject H0 if F > 3.18
F.05 = 3.18.

Hypothesis Testing About the

Variances of Two Populations
Selected Values from the F Distribution Table
Denominator Area in
Degrees
Upper
of Freedom
Tail
8
.10
.05
.025
.01
9

.10
.05
.025
.01

N umerator Degrees of Freedom

7
2.62
3.50
4.53
6.18

8
2.59
3.44
4.43
6.03

9
2.56
3.39
4.36
5.91

10
2.54
3.35
4.30
5.81

15
2.46
3.22
4.10
5.52

2.51
3.29
4.20
5.61

2.47
3.23
4.10
5.47

2.44
3.18
4.03
5.35

2.42
3.14
3.96
5.26

2.34
3.01
3.77
4.96

Hypothesis Testing About the

Variances of Two Populations

Test Statistic

TempKings sample variance is 1.768

ThermoRites sample variance is .700
2
s
F 1 =
2 1.768/.700 = 2.53
s2

Conclusion
We cannot reject H0. F = 2.53 < F.05 = 3.18.
There is insufficient evidence to conclude that
the population variances differ for the two
thermostat brands.

Hypothesis Testing About the

Variances of Two Populations

Determining and Using the p-Value

Area in Upper Tail

.10 .05
.025
.01
F Value (df1 = 9, df2 = 9) 2.44 3.18 4.03 5.35

Because F = 2.53 is between 2.44 and 3.18, the ar

in the upper tail of the distribution is between .10
and .05.

But this is a two-tailed test; after doubling the

upper-tail area, the p-value is between .20 and .10

Because = .10, we have p-value > and therefor

we cannot reject the null hypothesis.