330 CHAPTER 10 STATISTICAL INFERENCE FOR TWO SAMPLESEXAMPLE 10-1 A product developer is interested in reducing the drying time of a primer paint. Two formula-
tions of the paint are tested; formulation 1 is the standard chemistry, and formulation 2 has a
new drying ingredient that should reduce the drying time. From experience, it is known that
the standard deviation of drying time is 8 minutes, and this inherent variability should be un-
affected by the addition of the new ingredient. Ten specimens are painted with formulation 1,
and another 10 specimens are painted with formulation 2; the 20 specimens are painted in
random order. The two sample average drying times are minutes and
minutes, respectively. What conclusions can the product developer draw about the effective-
ness of the new ingredient, using 0.05?
We apply the eight-step procedure to this problem as follows:- The quantity of interest is the difference in mean drying times, 1 2 , and 0 0.
- We want to reject H 0 if the new ingredient reduces mean drying time.
- 0.05
- The test statistic is
where ^21 ^22 64 and n 1 n 2 10.
6. Reject H 0 : 1 2 if z 0
1.645z0.05.- Computations: Since minutes and minutes, the test statistic is
z 0 121 112B1822
101822
102.52x 1 121 x 2 1121822z ̨ 0 x 1 x 2 0B^21
n 1^22
n 2H ̨ 1 : 1
2.H ̨ 0 : 1 2 0, or H ̨ 0 : ̨ 1 2.x ̨ 1 121 x ̨ 2 112distribution when H 0 is true, we would takez and z as the boundaries of the critical re-
gion just as we did in the single-sample hypothesis-testing problem of Section 9-2.1. This
would give a test with level of significance. Critical regions for the one-sided alternatives
would be located similarly. Formally, we summarize these results below.
2
2Null hypothesis:Test statistic: (10-2)Alternative Hypotheses Rejection CriterionH ̨ 1 : 1 2 0 z 0 zH ̨ 1 : 1 2
0 z 0
zH 1 ̨: 1 2 0 z 0
z
2 or z 0 z
2Z 0 X 1 X 2 0B^21
n 1^22
n 2H 0 : 1 2 0c 10 .qxd 5/16/02 1:30 PM Page 330 RK UL 6 RK UL 6:Desktop Folder:TEMP WORK:MONTGOMERY:REVISES UPLO D CH114 FIN L:Quark Files: