Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Yuval Arbel <yuval.arbel@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | השב: st: marginal effects after gmm estimation |
Date | Wed, 05 Feb 2014 10:47:16 +0200 |
Dr. Yuval Arbel, School of Business, Carmel Academic Center,Haifa, Israel "Anat (Manes) Tchetchik" <anatmanes@gmail.com> wrote: >Dear all, > >I'm sorry for re-sending the question, I have looked in many sources >and haven't find the answer > >I have a count data model of two eqns, and endogenous variables, which >I have estimated using gmm (I have version 13.0) as follows:: > >gmm ($abroad) ($home), inst(`x')inst( `Z') twostep matrix(robust) >winit(unadj,indep) > >where the eqns, are Poisson models such that > >$abroad for example is: abroad- exp({xb1: `E'} + {b0})" > >I'm not sure how to calculate the marginal effects here >Do I have to calculate them manually such that. dy/dx= exp(xb)*b, > >Can I use instead the ivpoisson gmm wihch allows for mfx ? > >Best, >Anat >* >* 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/ * * 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/