Further to Arne's excellent points, note that the original posting did
not follow advice and indicate exactly what Yong typed. My guess,
agreeing with Martin Weiss, is that Yong just used an ambiguous
abbreviation. However, that's moot given the situation with -mixlogit-.
Nick
n.j.cox@durham.ac.uk
Arne Risa Hole
You have to use -mixlpred- to obtain predicted probabilities after
-mixlogit- as explained in the help-file. It doesn't work with
-asprvalue-. By the way it is helpful if you let people know when you
are asking questions about modules that are not part of official
Stata: -mixlogit- is downloadable from SSC and -asprvalue- is part of
J. Scott Long's SPost package
<http://www.indiana.edu/~jslsoc/spost.htm>.
Arne (author of -mixlogit-)
2008/10/14 Yong Yan <yong.yan@abs.gov.au>:
> I am using -asprvalue- to obtain predictions after the estimation of
> -mixlogit- with Stata 10. Somehow I got the error message such as "P
> ambiguous abbreviation". Can someone kindly tell me why this occurred?
*
* 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/
