07-30-2013 04:17 PM
Out of other options, I was wondering if I could calculate required sample size using #SAS for one of my surveys. Here are the details - population size: 6000; error tolerance: 5%; expected response rate: 25%; Confidence Interval: 95%. I know the answer but couldn't do it in SAS. Any help would be highly appreciated. Thanks, Ash
07-31-2013 10:00 AM
Read the SAS/STAT documentation about PROC POWER. If your survey is a complex sample survey with design effects and respondent sampling weights, you'll have to consider the estimated design effect [=the ratio of the variance for the complex survey to the variance from a survey using simple random sample] possibly from previous, similar surveys.
Need further help from the community? Please ask a new question.