Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Filip Van Droogenbroeck <filip.van.droogenbroeck@vub.ac.be> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: Getting Beta's with esttab after xtmixed |
Date | Fri, 19 Oct 2012 11:52:25 +0200 |
Hello, everybody, I'm trying to get beta's through esttab after running xtmixed. I found the following post: http://www.stata.com/statalist/archive/2008-05/msg00024.html which gives some information but I wonder how the beta's are calculated through esttab and if they can be trusted after xtmixed command? I'm doing the following: ******************************************************************** xtmixed SomHoudingJoden || schoolr:, mle variance estimates store m1 xtmixed SomHoudingJoden leeftijd geslacht || schoolr:, mle variance estimates store m2 esttab m1 m2, wide beta p nopar nostar transform(ln*: exp(2*@) 2*exp(2*@)) eqlabels("" "var(schoolr)" "var(_cons)" "var(Residual)", none) ********************************************************************* This gives me the beta's. Are these correct or are they only correct when doing normal linear regression? There is also no option in xtmixed to get beta's directly and this is also not available in other statistical programs it seems. Is their a good reason for this? Thank you very much, Kind regards, Filip Van Droogenbroeck * * 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/