I have cluster sampled data (88 PSUs) divided into 6 geographical strata and
want to post stratify based on 4 age classes from census data.
Is it possible with Stata9? Literature implies it.
If so, the problem: Following the Help directions I assigned postweights of
�the number of elementary sampling units in the population within each
poststratum� (88 PSU x 4 classes = 352 numbers) resulting in a �Population
size = 953� the census population size of one the PSUs. When I assigned
postweights based on strata (6 strata x 4 classes) the resulting �Population
size = 170593, is the size of one of the strata, not the size of the census
population of the study, 703,438.
The svyset commands used: svyset� psu [pw=pw_t], strata(strata) fpc(t_psu)
poststrat(ageC) postweight( pw_cpsu_age) ||� _n, fpc(cpsu_hh)
Any suggestions?
Thanks,
Joe
�
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
