Re: st: Mlogit with fixed effects

[Klaus Pforr <kpforr@googlemail.com>]

not yet. I'm working on such an ado 
(http://fmwww.bc.edu/repec/dsug2011/desug11_pforr.pdf). A first version 
of this ado will be available in a few weeks.

best

Klaus Pforr

Am 29.03.2012 17:11, schrieb Nick Cox:
> No. -xtlogit- just treats all non-zero values of the response as
> equivalent, so at best your multinomial response will get collapsed to
> a binary response and at worst it won't fly at all.
>
> If -xtlogit- were -xtmlogit- it would be called that.
>
> Others may have better advice on how best to do what you want.
>
> Nick
>
> Vanessa R. Wight [edited]
>
> > I am trying to run a mlogit with fixed effects.
> >
> > Can I run:
> >
> > xtlogit depvar indepvar, fe i(pid)
> >
> > if my dependent variable is multinomial with 5 values?
> >
> > Is there a Stata command for running a multinomial with fixed effects?
> >
> > I appreciate any help and guidance. Thanks so much,
> *
> *   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/


--
__________________________________

Klaus Pforr
MZES AB - A
Universität Mannheim
D - 68131 Mannheim
d__________________________________

*
*   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/