Dear Stata users:
I am trying to address selectivity bias in the estimation of an earnings function when selection is specified as a multinomial logit model. It is in my understanding that there are three different main approaches in the literature to do so, namely the Lee (1983) approach, the Dubin and McFadden (1984) approach, and a semi-parametric approach by Dahl (2002). I am wondering if anyone knows of any routine in Stata that allows implementing any of such procedures.
Thank you very much,
Monica
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
