Fatma Bircan
Middle East Technical University
Department of Economics
210-2032
Hi,
My model is as follows;
y1 = x1b1 + u1 1st selection eq. where y1=1 or 0
y2 = x2b2 + u2 2nd selection eq. where y2 = 1 or 0
y3 = x3b3 + u3
I estimate the first two equations using heckprob. Then I estimate a
regression equation including two lambda terms that I obtained from
heckprob estimation of selection equations. As far as I know there is
no stata module for the ML estimation of such models, with double
selection and an equation of primary interest. Therefore, I use a
two-step procedure to estimate the third equation. But, because of
selectivity, conventional estimates of the standard error of the
regression and the st. errors of the coeff. estimates is incosistent.
Can anyone tell me how to obtain consistent estimates of these
parameters in STATA.
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/
