----- Original Message -----
From: "Kenya Valeria Micaela de Souza Noronha" <[email protected]>
To: <[email protected]>
Sent: Saturday, June 21, 2003 2:01 PM
Subject: st: sample selection bias
> Dear all
>
> I need to estimate a model based on heckman method, but the selectivity is
> modelled as a multinomial logit. Is there any command in Stata for this
> model? How can i estimate it?
>
> thanks
>
> Kenya
>
If you go from the Stata homepage -> Links -> Stata Resources -> Programs,
you will find a program and paper to estimate linear regression models on a
selected subset of observations, where selectivity is modeled as a
multinomial logit (based on a two-step method).
Or you can install the file by typing within Stata
net from http://www.crest.fr/pageperso/lmi/gurgand
Hope this helps,
Scott
*
* 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/
