Hello,
I am estimating a recursive bivariate probit model of the form
y1 = x1 + x2 + e1
y2 = x1 + x2 + x3 + y1 + e2
I would like to obtain marginal effects and their associated standard
errors for each independent variable.
The new "margins" command does not seem to work with the recursive
structure, giving me an error that the stochastic component of my
model prevents estimation. I have searched the statalist archives,
and saw similar questions asked before, but without any satisfactory
answer. I can derive the marginal effects easily enough on my own
using Greene's methods, but the standard error calculations gave me a
lot more trouble.
So my question is: is there a relatively painless way I can get
these parameters in STATA?
Thank you very much for your help.
Doug
*
* 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/
