where x2n - 1,a>2 is the number for which

P1 x2n - 1 7 x2n - 1,a>2 2 =

a
2
and x2n - 1,1 - a>2 is the number for which

P1 x2n - 1 6 x2n - 1,1 - a>2 2 =

a
2
and the random variable x2n - 1 follows a chi-square distribution with (n - 1) de-
grees of freedom.

Although it is assumed throughout this section that the population is normally dis-
tributed, we should always check for any evidence that this assumption fails. Notice that
the confidence interval in Equation 7.10 is not the usual form, sample point estimator {
margin of error.

Example 7.7 Comparing Temperature Variances

(Confidence Interval)
The manager of Northern Steel, Inc., wants to assess the temperature variation in the
firm’s new electric furnace. It is known that temperatures are normally distributed. A
random sample of 25 temperatures over a 1-week period is obtained, and the sample
variance is found to be s 2 = 100. Find a 95% confidence interval for the population
variance temperature.

Solution Here, n = 25 and s 2 = 100, and for a 95% confidence interval, a = 0.05. It
follows from the chi-square distribution in Appendix Table 7 (see Figure 7. 14) that
x2n - 1,1 - a>2 = x224,0.975 = 12.401 and x2n - 1,a>2 = x224,0.025 = 39.364

From Equation 7.10, the lower confidence limit for a 95% confidence interval for
the population variance is given by
1 n - 1 2s 2 1 24 21 100 2
LCL = 2
= = 60.97
xn - 1,a>2 39.364

and from Equation 7.10, the upper confidence limit is found as follows:
1 n - 1 2s 2 1 24 21 100 2
UCL = 2
= = 193.53.
xn - 1,1 - a>2 12.401

Figure 7.14 Chi-Square Distribution for n = 25 and 95% Confidence Level

0.95

0.025 0.025

x 2(24,0.975) = 12.401 x 2(24,0.025) = 39.364

308 Chapter 7 Confidence Interval Estimation: One Population

 Example 7.4 Trucks: Gasoline Consumption
(Confidence Interval)
Recently gasoline prices rose drastically. Suppose that a study was conducted using
truck drivers with equivalent years of experience to test run 24 trucks of a particular
model over the same highway. Estimate the population mean fuel consumption for this
truck model with 90% confidence if the fuel consumption, in miles per gallon, for these
24 trucks was as follows:

15.5 21.0 18.5 19.3 19.7 16.9 20.2 14.5

16.5 19.2 18.7 18.2 18.0 17.5 18.5 20.5
18.6 19.1 19.8 18.0 19.8 18.2 20.3 21.8

The data are stored in the data file Trucks.

Solution We check the normality assumption by constructing the normal probability

plot. Figure 7.9 does not provide evidence of nonnormality.

Figure 7.9 Normal Probability Plot

Next, calculating the mean and standard deviation, we find the following:

x = 18.68 s = 1.69526 tn - 1,a>2 = t23,0.05 = 1.714

By Equation 7.6 the 90% confidence interval is as follows:

= 18.68 { 1 1.714 2 * 1 0.3460 2

s 1.69526
x { tn - 1,a>2 = 18.68 { t23,0.05
1n 124
= 18.68 { 0.5930

The lower confidence limit is approximately equal to 18.1, and the upper confidence limit
is approximately equal to 19.3. Figure 7.10 is the Excel output of descriptive statistics
generated for the data file Trucks.
The interpretation of the confidence interval is important. If independent random
samples of 24 trucks are repeatedly selected from the population and confidence in-
tervals for each of these samples are determined, then over a very large number of
repeated trials, 90% of these intervals will contain the value of the true mean fuel con-
sumption for this model truck. In practice, however, one does not repeatedly draw
such independent samples.

300 Chapter 7 Confidence Interval Estimation: One Population