[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Poisson Model with endogenous dummy variable

From   Partha Deb <>
Subject   Re: st: Poisson Model with endogenous dummy variable
Date   Wed, 20 Feb 2008 13:23:39 -0500


I have code for a negative binomial outcome and binary treatment model estimated using maximum simulated likelihood. It should fit your case well. It also estimates models for gamma-distributed outcomes. You can get the package, -treatreg2-, by typing

net from

from the command line in Stata.



Austin Nichols wrote:

I think Mullahy published a GMM estimator for this specific case, but
if you are willing to treat the endogenous dummy as continuous, you

ssc inst ivpois
probit x otherx* z*
predict phat
ivpois y otherx*, endog(x) exog(phat)

until you find a better estimator.

On Feb 20, 2008 11:21 AM,  <> wrote:
dear all,
I would like to estimate a poisson model which includes an endogenous
dummy variable. To be more precise, this dummy captures a "treatment
effect", hence I would like to model the selection process that
underlies it by a probit model, and use the fitted probabilities as
instruments for the dummy.
Does anyone of you know a Stata command (either built in or not) that
allows to estimate such a model?
thank you very much for any help

*   For searches and help try:
Partha Deb
Department of Economics
Hunter College
ph:  (212) 772-5435
fax: (212) 772-5398

Emancipate yourselves from mental slavery
None but ourselves can free our minds.
	- Bob Marley

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index