A Questionnaire Is Designed to Investigate Attitudes About Political Corruption

Short Answer

A questionnaire is designed to investigate attitudes about political corruption in government. The experimenter would like to survey two different groups--Republicans and Democrats--and compare the responses to various "yes-no" questions for the two groups. The experimenter requires that the sampling error for the difference in the proportion of yes responses for the two groups is no more than 4 percentage points with probability equal to 0.95. If the two samples are both the same size, how large should the samples be?
______________