Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | "Achilleas Vassilopoulos" <axivas@yahoo.gr> |
| To | <statalist@hsphsun2.harvard.edu> |
| Subject | st: using svy estimation to control for the absence of regional variables? |
| Date | Fri, 26 Mar 2010 23:06:44 +0200 |
Dear all, I'm using the NHANES dataset and I want to get the predicted probability of a probit model including the state or country of residence of the respondent in the set of independent variables. Since this information is held confidential in NHANES 2005-6, my question is if anyone knows whether I get the desired results (or at least good approximations), in the absence of such variables, when I use 'predict' after a 'svy : probit' estimation? Pseudo-PSU, Pseudo-strata and p-weights are available in the dataset. Achilleas Vassilopoulos Agricultural University of Athens, Dept. of Agricultural Economics and Rural Development, Lab. of Political Economy and European Integration Iera Odos 75, 11855, Athens, Greece Tel : (+30) 210-5294726 Fax : (+30) 210-5294786 Email: avassilopoulos.aua@gmail.com * * 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/