I searched the archive to no avail, so here goes. I am using ivprobit.
My endogenous variable of interest is ordinal (it’s called “custcode”
and ranges from 1-5). I’m interested in obtaining predicted
probabilities for each of its values. From what I can gather, the best
approach is “mfx, predict(p) at(custcode=1) nose,” “mfx, predict(p)
at(custcode=2) nose,” etc. If this is right, can someone please advise
on exactly how to interpret the reported dy/dx value? Say custcode is
set to 3 and the resulting dy/dx is .06. The .06 would mean what
exactly? As I understand it, the number at the top of the output is the
probability of a positive outcome when all variables are set at their
mean, but how exactly is the dy/dx value for custcode distinguished
from that?
Thanks, John W.
---------------------------------
John L. Worrall
Professor of Criminology
Editor, Police Quarterly
The University of Texas at Dallas
800 West Campbell Road, GR 31
Richardson, TX 75080-3021
(972)883-4893
*
* 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/
