334 CHAPTER 10 STATISTICAL INFERENCE FOR TWO SAMPLEScause and effect here has proven enormously difficult. Many individuals had decided to
smoke long before the start of the research studies, and many factors other than smoking could
have a role in contracting lung cancer.10-2.4 Confidence Interval on a Difference in Means,
Variances KnownThe 100(1)% confidence interval on the difference in two means 1 2 when the vari-
ances are known can be found directly from results given previously in this section. Recall
thatX 11 , X 12 ,p, is a random sample ofn 1 observations from the first population and X 21 ,
X 22 ,p, is a random sample ofn 2 observations from the second population. The difference
in sample means is a point estimator of 1 2 , andhas a standard normal distribution if the two populations are normal or is approximately stan-
dard normal if the conditions of the central limit theorem apply, respectively. This implies that
, orThis can be rearranged asTherefore, the 100(1)% confidence interval for 1 2 is defined as follows.P aX 1 X 2 z
2
B^21
n 1^22
n 2 ^1 ^2 X^1 X^2 z^2 B^21
n 1^22
n 2 b^1 P ≥z
2 X 1 X 2 1 1 22B^21
n 1^22
n 2z
2 ¥ 1 P 1 z
2 Zz
22 1 ZX 1 X 2 1 1 22B^21
n 1^22
n 2X 1 X 2X 2 n 2X 1 n 1If and are the means of independent random samples of sizes n 1 and n 2 from
two independent normal populations with known variances ^21 and 22 , respectively,
a100(1)% confidence interval for 1 2 is(10-7)where z 2 is the upper 2 percentage point of the standard normal distribution.x 1 x 2 z
2
B^21
n 1^22
n 2 ^1 ^2 x^1 x^2 z^2 B^21
n 1^22
n 2x 1 x 2DefinitionThe confidence level 1is exact when the populations are normal. For nonnormal popu-
lations, the confidence level is approximately valid for large sample sizes.c 10 .qxd 5/16/02 1:30 PM Page 334 RK UL 6 RK UL 6:Desktop Folder:TEMP WORK:MONTGOMERY:REVISES UPLO D CH114 FIN L:Quark Files: