Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: -xtlogit- produces different results under different versions


From   rgutierrez@stata.com (Roberto G. Gutierrez, StataCorp)
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: -xtlogit- produces different results under different versions
Date   Fri, 26 Sep 2008 10:16:10 -0500

Zhiqiang Wang <z.wang@uq.edu.au> writes:

> While trying to update on an old ado file to include -xtlogit- command for
> my Australian colleague, we noticed that using the same data, -xtlogit-
> produces different results.

and then goes on to demonstrate the differences between Stata 8, 9, and 10.

Vince Wiggins <vwiggins@stata.com> posted on this issue a few weeks ago:

http://www.stata.com/statalist/archive/2008-09/msg00244.html

His post is in reference to -xttobit-, but what is stated there holds true for
-xtlogit- as well.  To summarize, over the last two versions of Stata we have
twice improved the way we approximate the log-likelihood through numerical
integration.

--Bobby
rgutierrez@stata.com
*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index