Dear all,
I am estimating an ordered probit model with a heckman selection correction (ordinary probit) using David Roodman’s cmp-ado.
I need to compute the conditional marginal effects for the ordered probit equation, that is Pr(depvar=1 | depvar_s=1) for outcome(1), Pr(depvar=2 | depvar_s=1) for outcome(2), and so on.
Due to the generality of cmp, this is not possible via margins or mfx.
Has anybody already done this or might be able to provide me with useful hints?
Thanks in advance.
*
* 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/
