Bookmark and Share

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]

Re: st: Mlogit: Log pseudolikelihood bug?


From   Maarten buis <[email protected]>
To   [email protected]
Subject   Re: st: Mlogit: Log pseudolikelihood bug?
Date   Sun, 27 Feb 2011 12:48:22 +0000 (GMT)

--- On Sun, 27/2/11, Robert L. Hellpap wrote:
> I tried to estimate a quiete complex model with more than
> 100 dummy's as independent on a 6 category dependent
> variable. When my results where displayed the log
> pseudolikelihood value was announced as ".z_" which should
> be a missing value. What does ist mean that the log
> pseudolikelihood is a missing value and is it legitime to
> reduce the number of iterations until I receive a legal
> value?

It means that you need to simplify your model. Remember that
the trick of adding dummies to get a fixed effects regression
does not work for non-linear models like -mlogit-, so the
value of adding that many dummies is often doubtful anyhow.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index