Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Berg, Marrit van den" <Marrit.vandenBerg@wur.nl> |
To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
Subject | st: system with endogenous censored and probit regressors |
Date | Mon, 7 Nov 2011 14:03:43 +0100 |
I am trying to estimate the following model: Y1 = a0+a1Y2+a2X+a3Z1+e1 Y2=b0+b1Y1+b2X+b3Z2+e2 (a2,a3,b2,b3, X,Z1,Z2 are vectors) With Y1 and Y2 continuous variables, the approach would be to estimate both equations using 2SLS with in the first stage the reduced form equation of the other equation. However, Y1 is a dummy variable (0,1) and Y2 is censored at 0. What is the appropriate estimation strategy in this case? Thank you for your assistance. Marrit van den Berg * * 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/