Dear Statalisters,
In selecting variables to use in the selection equation of a heckman
model, what do I need to look out for?
Are the restrictions as strict as in instrumental variables
estimations? Is it enough that the variables are significant in the
selection equation, but not significant when added to the main
regression of interest? I do not see people reporting any tests in
other papers I have, as they frequently do with IV-regressions.
Thank you for your time.
Tinna
PS. This question has be asked twice before on Statalist (once by me
and once by another user). It didn't get any answers either time, but
someone has to know. Sorry about the redundancy.
*
* 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/
