Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Zhe Ren <zheren@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: xthtaylor with sampling weight |
Date | Fri, 23 Apr 2010 00:22:08 -0300 |
Dear statalisters, I'm dealing with panel data with possible endogenous regressors. So I'm considering xthtaylor command which is random-effects model accommodating correlation between some regressors and individual effects. However, my dataset comes from a survey and there is sampling weights (reciprocal of sampling probability) along with the data. I would like to apply this sampling weights when I estimate my model using hausman-taylor estimator. As most of you already found, pweight is not allowed in random-effects panel models in stata! I was reading through the help notes and only got to know that the sampling weight has to be constant across years for the cross-sectional units. My question then is stragihtforward: the sampling weights ARE constant across years for each cross-sectional units in my dataset (in other words, it is a perfectly balanced panel). But how can I apply pweight in xthtaylor? Any help would be greatly appreciated! Jerry * * 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/