RE: st: heckprob or biprob and getting lamda terms

["naceur khraief" <naceur_khraief@hotmail.com>]

To estimate a sample selection model (cross-section) with stata we have two 
commands:
� heckman � et � heckprob �. "heckman" is used with the continous dependent 
variable.  Stata also includes another selection model the "heckprob" which 
works in a manner very similar to heckman except that the response variable 
is binary. The "heckprob" command shares a number of features with 
"biprobit" models.Both involve two equations, both of which are probit 
models. Both have correlated residuals from the two equations. now to obtain 
lambdas (the inverse Mills ratio) we can do some transformations.

Heckprob .......
predict p1, xb
generate phi = (1/sqrt(2*_pi))*exp(-(p1^2/2)) /*standardize it*/
generate capphi = norm(p1)
generate invmills = phi/capphi
regress depvar indepvar invmills



> From: fatma bircan <bircan@metu.edu.tr>
> Reply-To: statalist@hsphsun2.harvard.edu
> To: statalist@hsphsun2.harvard.edu
> Subject: st: heckprob or biprob and getting lamda terms
> Date: Tue, 07 Dec 2004 15:46:19 +0200
>
> Hi,
>
> I am trying to estimate an earnings equation for self-employed and
> employed. To eliminate the selection bias I intend to use a double
> probit model. Stata seems to offer two commands for this task,
> heckprob and biprobit. I am not sure which one I should use.
>
> Heckprob seems to be more appropriate for my model. But, in any case I
> need to get two selection terms (lambda s) for my earnings equations.
> With heckprob command I only get the rho term but lambdas. I can
> neither add the main equation (earnings eq.) with heckprob command.
>
> Anyone familiar with the problem please write me.
>
> Thank you
>
>
>
>
>
> *
> *   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/
_________________________________________________________________
Partagez une seule photo ou un diaporama complet dans MSN Messenger. 
http://join.msn.com/?pgmarket=fr-ca&page=features/messenger Commencez d�s 
maintenant � profiter de tous les avantages de MSN Premium et obtenez les 
deux premiers mois GRATUITS*.

*
*   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/