Mariam,
Take a look at Fran�ois Bourguignon, Martin Fournier, and Marc Gurgand's
-selmlog- at http://www.crest.fr/pageperso/lmi/gurgand/selmlog.htm
Selection Bias Correction Based on the Multinomial Logit Model
Fran�ois Bourguignon, Martin Fournier, Marc Gurgand
"Abstract: In a widely quoted paper, Lee (1983) proposed a generalization of
the two-step method selection bias correction introduced by Heckman (1979)
that allows for any parameterized error distribution instead of simply
bi-variate normal. In the second part of his paper, Lee extended his method
to the case where selectivity is modeled as a multinomial logit. In this
note, we show that the result he then obtained relies on a very unlikely
particular case and we provide an easily implementable correction method to
get consistent estimates based on usual parametric assumptions."
Scott
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of mariam hassan
> Sent: Monday, February 21, 2005 7:53 PM
> To: [email protected]
> Subject: st: sample selection model with more than 2 choices
>
> Does Stata do Heckman selection model with more than 2 choices? I have
> more than 2 (actually 4) treatment groups. I am not sure if the stata
> commands like heckman or heckprob can help me. Are there modified
> versions
> of these commands to analyze selection model with more than 2 choices in
> stata.
>
> Is there anaother way to calculate an estimator for the selection model
> with
> a mulltinomial selection.
>
> Thanks
> Mariam
>
> _________________________________________________________________
> Manage information better. Optimise your tasks.
> http://www.microsoft.com/india/office/experience/ Experience MS Office
> System.
>
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
