I'm trying to find confidence intervals for the means of various variables in a database using SPSS, and I've run into a spot of trouble.

The data is weighted, because each of the people who was surveyed represents a different portion of the overall population. For example, one young man in our sample might represent 28000 young men in the general population. The problem is that SPSS seems to think that the young man's database entries each represent 28000 measurements when they actually just represent one, and this makes SPSS think we have much more data than we actually do. As a result SPSS is giving very very low standard error estimates and very very narrow confidence intervals.

I've tried fixing this by dividing every weight value by the mean weight. This gives plausible figures and an average weight of 1, but I'm not sure the resulting numbers are actually correct.

Is my approach sound? If not, what should I try?

I've been using the Explore command to find mean and standard error (among other things), in case it matters.

  • $\begingroup$ Weighting in SPSS is frequency weighting, so weight 28000 indeed means that there are 28000 identical men. You say, your man represent 28000 men in the population. Well, if the total population size is N and your sample size is n, set the weight for the man to 28000/N * n. $\endgroup$ – ttnphns Jun 3 '14 at 7:21
  • $\begingroup$ Please avoid cross posting the questions simultaneously, stackoverflow.com/q/24006790/604456, and make sure to link between them when you do. $\endgroup$ – Andy W Jun 3 '14 at 14:59
  • $\begingroup$ Oops, didn't know crossposting was discouraged. I'll avoid it in the future. $\endgroup$ – Philippe Saner Jun 3 '14 at 17:02

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.