Applied Statistics and Probability for Engineers

482 CHAPTER 13 DESIGN AND ANALYSIS OF SINGLE-FACTOR EXPERIMENTS: THE ANALYSIS OF VARIANCE

This suggests that time or run order is important or that variables that change over time are

important and have not been included in the experimental design.

A normal probability plot of the residuals from the paper tensile strength experiment is

shown in Fig. 13-3. Figures 13-4 and 13-5 present the residuals plotted against the factor

levels and the fitted value respectively. These plots do not reveal any model inadequacy or

unusual problem with the assumptions.

13-2.6 Determining Sample Size

In any experimental design problem, the choice of the sample size or number of replicates to

use is important. Operating characteristic curvescan be used to provide guidance in mak-

ing this selection. Recall that the operating characteristic curve is a plot of the probability of a

yi.

–2

–1

–4 0246

–2

0

1

2

Normal score z

j

Residual value

Figure 13-3 Normal probability plot of residuals from

the hardwood concentration experiment.

5%

2

4

0

• 2


• 4

10% 15% 20%

Residual value

Figure 13-4 Plot of residuals versus factor levels

(hardwood concentration).

y–i•

2

4

0

• 2


• 4

20.0 25.0

Residual value

10.0 15.0

Figure 13-5 Plot of residuals versus yi.

c 13 .qxd 5/8/02 9:20 PM Page 482 RK UL 6 RK UL 6:Desktop Folder:TEMP WORK:PQ220 MONT 8/5/2002:Ch 13: