Re: st: Probit Fe question

[Stas Kolenikov <skolenik@gmail.com>]

The "fixed effects" estimators are conditional estimators that utilize
certain sufficient statistics via factorization of the likelihood.
This is doable with Gaussian models (linear fixed effect), binary
models (fixed effect logit) and Poisson. This, however, is the
exhaustive list; in particular, there is no "fixed effect probit".

On Sun, Oct 3, 2010 at 3:12 AM, Carolina Herrera
<cherrera@thecenter.ucsf.edu> wrote:
> Hi everyone,
>
> I've been digging around the web and my econometric texts looking for a consistent set of answers on how to estimate a fixed-effect probit.  I've reviewed Greene(2004), Wooldridge (2005 & the panel data text book), half a dozen journal articles, and Statalist.  What I could not find was
>
> (1) agreement on the current "best method" for addressing the incidental parameters problem
> (2) code to implement either the Heckman "zig-zag" solution  or to implement another solution without much programming
> (3) a stata example where someone performs a fixed effecs probit and explains their interpretation.
>
> I realize that this a lot to ask of the list participants, but has anyone addressed these questions for a class or paper, and would they be willing to share their opinions/code/examples?  If you've already done so and I missed it during my perusal of the archives, I apologize in advance.
>
> thanks for your time,
> Carolina
>
> Carolina Herrera, MA
> The Center for the Health Professions
> University of California, San Francisco
>
>
> *
> *   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/
>



-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.

*
*   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/