Re: st: svy: confidence interval using subpop vs. cross-tabulation

[sjsamuels@gmail.com]

I cannot tell for sure, because you did not show us your -svyset-
command or any of the Stata output (as the FAQ ask). This might happen
if region is a stratum variable. In that case, it should not be used
as  sub-population.

Steve
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/