Statalist The Stata Listserver


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

st: help with Heckman


From   "Teresa Casey" <tjcasey@ucdavis.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: help with Heckman
Date   Wed, 15 Nov 2006 18:40:31 -0800

I need some help with the FLM and two-step Heckman commands in Stata 9 (or
8). My data requires the use of cluster and individual weighting, which are
causing some problems with the command. If I choose to specify weights
myself, it only allows me to put the weight option at the end of the
substantive equation-do the weights apply to the selection equation as well?
How can I specify for the cluster variable? If I use the svy: Heckman
command, I can not use the twostep option. My questions are: How can I use
Heckman twostep and still weight the analysis appropriately?

As an alternative I estimated a probit model with weights to predict the
probability of the selection variable. I used the results to construct
an inverse mills ratio. I then added the IMR to the substantive OLS
model with weights, in essence controlling for the probability of the
selection variable. Is this an acceptable alternative to using the
Heckman command?

I would appreciate any help I can get with this.
Thanks,
Teresa

Teresa Casey, M.A.
Sociology, UC Davis
Office phone 530-754-9484


*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index