Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | qingjing zhang <qjzhang1014@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: Constant in logit panel fixed and panel logit 2SLS |
Date | Sat, 8 Feb 2014 17:13:32 +0000 |
Thanks! On 8 February 2014 02:37, Steve Samuels <sjsamuels@gmail.com> wrote: > > > > >> >> On Feb 7, 2014, at 5:14 PM, qingjing zhang <qjzhang1014@gmail.com> wrote:, >> >> I am using panel logistic regressions on my data with Stata 12. >> However, I met some difficulties. >> >> First, I do not understand why the logit fixed effect command >> (xtlogit, fe) produce a regression without a constant term. > > > Because -xtlogit- is equivalent to conditional logistic regression (-clogit-) as the > Manual entry makes clear (p.232 XT ) > > > Typing > . xtlogit , fe > is equivalent to typing > . clogit , group(varname i) > >> >> Second, to solve the endogeneity problem, I need to use the 2SLS for >> the panel logit model. I checked some reference, and found that I >> could do the panel 2SLS using (xtivreg) and logit 2SLS using >> (ivprobit) or (sspecialreg). However, I do not know how to do the >> logit panel 2SLS in STATA. > > > I don't know the answer to this one. Note that correct spelling is "Stata" not "STATA" >> > > Steve Samuels > sjsamuels@gmail.com > * > * 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/