Not really. -selmlog- assumes that the endogenous variable is continuos but
censored (e.g. wages).
-selmlog- could be seen as an alternative to the Heckman two-stage procedure
where instead of correcting for the non-observed distribution using a probit
a multilogit is used. The variable of interest is the continuos one however
the results from the multilogit are presented. Therefore this might be what
Leopoldo is looking for.
Hope this helps,
Rafa
----- Original Message -----
From: "Joao Pedro W. de Azevedo" <[email protected]>
To: <[email protected]>
Sent: Tuesday, March 09, 2004 4:45 PM
Subject: st: RE: estimating a system with continuous +discrete variables
> I'm sorry... Selmlog only works when the endogenous variable is
> plichotomous... Please disregard my suggestion.
> JP
>
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of Leopoldo
Avellan
> Sent: Tuesday, March 09, 2004 3:41 PM
> To: [email protected]
> Subject: st: estimating a system with continuous +discrete variables
>
>
> Hi
>
> I want to estimate a system of equations, in which, one endogenous
variable
> is continuous and the other is polichotomous and discrete (ordered probit
> or logit).
>
> I found the routine CDSIMEQ but this one works if the discrete variable is
> dichotomous and not polichotomous.
>
> Does anyone know how to estimate this sytem with 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/
>
> *
> * 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/
