Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Freitas, Derek" <Derek.Freitas@med.nyu.edu> |
To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
Subject | st: svy: heckprob diagnostics |
Date | Fri, 9 Aug 2013 14:18:03 +0000 |
Hello Everyone, I'm currently running a bivariate probit model with sample selection in Stata 12 (svy: heckprob) My selection model is whether the person has been tested for Hepatitis C. My outcome model is whether the person was told they have HCV after being tested. i.e., heckprob hcv_pos x1 x2, select(hcv_test = x1 x2 x3) I'm aware of some basic methods of assessing model quality/fit/specification when using heckprob on its own, but I'm at a loss as how to assess model quality when heckprob is coupled with svy: I've dug through every single resource I could find (Statalist, Stata Journal/Manual, online articles, etc.) and have come up relatively empty handed. Is anyone aware of any methods of judging the quality of a svy: heckprob model? Thanks, Derek Freitas * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/