Dear statalisters,
this is my problem.
A worker can be in 4 labor market status.
I want to run a wage regression for each status.
I create 4 "inverse mills ratio" from a multinomial
logit which explains in which status the worker is.
I run 4 wage regression (one per status), including in
each one only the 'inverse mills ratio' for that
status (meaning, how likely it is that the worker is
found in that status).
When I want to perform the Oaxaca decomposition with
the command oaxaca, I have the problem that each
regression has a different selection term, a different
'inverse mills ratio'. So, one of the independent
variables is different in each of the regressions I
want to compare.
How should I proceed?
Thank you very much in advance,
Marco
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
*
* 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/