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: RE: statalist-digest V4 #4467
From
"Bromiley, Philip" <[email protected]>
To
"[email protected]" <[email protected]>
Subject
st: RE: statalist-digest V4 #4467
Date
Mon, 26 Mar 2012 10:15:10 -0700
Ben,
I've tried that as well and had the same problem of not converging. After trying all the optimizing tricks (difficult, switching optimization procedure, etc.) without success, I found it estimates with the twostep option (which it says is Newey's two-step estimator).
Phil
Philip Bromiley
Dean's Professor of Strategic Management
Merage School of Business
University of California, Irvine
Irvine, CA 92697-3125
(949) 824-6657
Date: Sat, 24 Mar 2012 23:38:51 +0100
From: Benjamin Niug <[email protected]>
Subject: st: -ivprobit- not converging
Hi guys,
I am having the following problem:
I want to run a probit regression using Instrumental Variables and I am account for fixed effects using dummy variables using the
- -ivprobit- command. While the simple regressions seem to be calculated, I am getting error messages for the IVProbit regressions including interaction terms: The optimality algorithm is "not converging" even after several hundred iterations and the calculated likelihood does not change anymore after about 100 iterations. Does anybody of you know how to overcome this problem? Is there a (better) possibility to estimate a binary choice model using IV and accounting for fixed effects?
Best regards,
Benjamin
*
*
* 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/