Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Marian <yomarianopereira@yahoo.com.ar> |
| To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
| Subject | st: bivariate probit in first stage of heckman model |
| Date | Tue, 23 Aug 2011 10:22:30 -0700 (PDT) |
Dear all, I'm estimating a model for the export share, and to correct the selection bias i use the Heckman model my doubt is because in the first stage to calculate the inverse of mills i use a bivariate probit model instead of a probabilistic model. My question is if it's valid here is the syntax biprobit (x1 y1 x2 y2) (x2 y2 x3), robust Predictive p11, p11 generate phi = (1/sqrt (2 * _pi)) * exp (- (p11 ^ 2 / 2)) / * standardize it * / generate capphi = normal (p11) generate invmills = phi/capphi reg x1 x2 x3 invmills2 export_share, robust thank you! Mariano * * 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/