Re: st: "predicts failure perfectly" in binary logit

[Kai Arzheimer <arzheimer@politik.uni-mainz.de>]

David,
as usually, the short answer to your question would be 'it depends'. I 
suggest you have a look a recent article by Christopher Zorn that 
discusses the problem of separation which is behind the error message. 
Reading that paper will probably help you to make an informed decision.
The reference is:

@article{,
   Author = {Zorn, Christopher},
   Title = {A Solution to Separation in Binary Response Models},
   Journal = {Political Analysis},
   Volume = {13},
   Pages = {157-170},
   Year = {2005} }

Best
Kai
--
Institut für Politikwissenschaft
Colonel-Kleinmann-Weg 2 / D-55099 Mainz
Tel: 49-6131-39-23782 / Fax: 49-6131-39-22996
* http://www.politik.uni-mainz.de/kai.arzheimer/Welcome.html
*
*   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/