----------------------------------------------------------------------
----------
Aimee,
Check the following -help heckman-
Rodrigo.
----- Original Message -----
From: "Aim�e R. Dechter" <[email protected]>
To: <[email protected]>
Sent: Tuesday, June 20, 2006 12:10 PM
Subject: st: Categorical Model with binary selection equation
Hello,
I am estimating a categorical data model that is based on earnings;
therefore, I am missing observations for the population that does not
work. I would be grateful if you could tell me whether there is a way
in STATA (or some other software) to estimate this model with an
adjustment for the selection into/out of employment? My selection
equation is binary, but the substantive equation estimates a
categorical variable with many categories. Is there something like the
Heckprob procedure, except the substantive outcome has more than two
categories?
There appears to be discussion on the stata list about Heckman models
that have multinomial logit selection equations; however, I am looking
for a STATA procedure with the standard binary selection equation. In
my case it is the substantive outcome that has multiple categories. If
Heckprob is a probit model with selection, does a multinomial probit
or logit model with selection exist in STATA or some other stat
package?
Thank you very much for your time.
Aim�e Dechter
University of Wisconsin-Madison
1180 Observatory Drive
Madison, WI 53706
[email protected]
*
* 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/