Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: > mfx from probit for variables for which I initially get the message "predicts failure perfectly" >
From
Luca Fumarco <[email protected]>
To
"[email protected]" <[email protected]>
Subject
st: > mfx from probit for variables for which I initially get the message "predicts failure perfectly" >
Date
Tue, 24 Apr 2012 12:00:28 +0200
Dear Statalisters,
I am using a probit model, and for a couple of variables I receive the message "predicts failure perfectly".
There is no convergence.
However, since it is a probit model, when I am interested in are the marginal effects.
Thus, I go on and use mfx, Stata produces the marginal effects of those couple of variable too.
Are those values meaningful? Or I should change strategy, switching to firthlogit (which cope with the problem of separation)
Luca Fumarco
Ph.D. Student
Linnæus University
*
* 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/