Fatma Bircan
Middle East Technical University
Department of Economics
210-2032
Hi,
I am interested in calculating the selection correction terms
(analogous to inverse mills ratio after univariate probit model) afetr
ML estimation of selection equations with heckprob. To obtain lambda
terms, I do the following calculations. Instead of rho I use the rho
value I obtained from heckprob estimation. Is that OK? What is the
athrho for? Can onyone tell me that my calculations are correct or are
there any mistake. Particularly, I am concerned whether "binorm"
command is appropriate in calculating the bivariate normal
distribution with the correlation term rho.
predict xbsw, xb
predict xblfp, xbsel
gen binrom=binorm( xbsw, xblfp, rho)
gen P=(xblfp-(rho)*(xbsw))/sqrt(1-rho^2)
gen S=(xbsw-(rho)* (xblfp))/sqrt(1-rho^2)
gen lambdaP=(normd( xblfp)*normprob( S))/ binrom
gen lambdaS=(normd( xbsw)*normprob(P))/ binrom
Thank you
*
* 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/
