Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Rao, James" <James.Rao@agr.uni-goettingen.de> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | st: Re: endogeneity in heckman selection model |
Date | Tue, 6 Apr 2010 17:53:47 +0200 |
Dear Statalisters, I am estimating a labor demand equation that is "incidentally truncated" in the words of W. H. Green (2006), since demand for hired labor is only observed for those who actually hire labor. However, I am more interested in the effect of a treatment variable on labor demand and I suspect that the same treatment variable also has an effect on the selection equation - determining whether or not one uses hired labor. Therefore I end up with the usual Heckman selection model but with a potentially endogenous variable in both the selection and the labor demand equation. Could there be an approach that can allow me to handle the endogeneity problem in this scenario. ================================================== Rao E.O. James (Msc) Research Associate/PhD Student Department of Agricultural Economics and Rural Development Georg-August University of Göttingen Platz der Gottinger Sieben 5 37073 Göttingen, Germany. Tell:+49-551-394443 (Office) E-mail: jimrao2@yahoo.co.uk; James.Rao@agr.uni-goettingen.de Courage is not the absence of fear but the triumph over it ... so fear not to fear ... but strive to overcome fear! * * 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/