Suppose that you consider the confidence interval found in Q…
Suppose that you consider the confidence interval found in Question 22 to be too wide. You want to be able to estimate the difference between the two population proportions with a sampling error of no more than SE=0.03 (or 3%) at the 95% confidence level. To be conservative, assume that no reliable estimate for p1 and p2 are available, so use p1=p2=.5 for your computations. If you going to use independent random samples of the same size, how large should the sample sizes be?
Read Details