Dear,
I would like to compare the marginal effects of a
Tobit (intreg) model with those of an OLS (reg) model.
For the Tobit model I am interested in the marginal
effects on y conditional on y > 0 (with 0 as the
censoring value), or in STATAspeak: mfx, predict
e(0,.).
Normally, I would use suest to compare across models
however I can only get suest to estimate the marginal
effects on the latent dependent variable (i.e. mfx,
predict(xb)) which are given by default as they are
the same as the reported coefficients.
Any suggestions are greatly appreciated!
Happy holidays,
Bart
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
*
* 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/
