Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Maximum iterations exceeded with predictnl


From   rgutierrez@stata.com (Roberto G. Gutierrez, StataCorp)
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Maximum iterations exceeded with predictnl
Date   Wed, 22 Sep 2004 17:53:18 -0500

In response to my recommendation to use -mlogpred-, Matthew R. Polisson
<matthew.polisson@gmail.com> writes:

> Thanks very much for your help. The mlogpred command works quite nicely. Is
> there a similar command which follows logit? I am assuming that predictnl
> works after logit, although I can imagine running into similar iteration
> problems.

I don't know of an equivalent program for -logit-, however, you are unlikely
to get convergence problems using -predictnl- after -logit-, since the
calculation for predicted probabilities after -logit- is fairly sturdy.  If
you do run into problems, I'd be most interested to have a look at your data
and model.

On another note, you can use -mlogit- to fit a -logit- model, e.g. with the 
auto dataset

    . mlogit foreign turn displacement, base(0)

vs.

    . logit foreign turn displacement

and thus still use -mlogpred-.  Yeah, using -mlogit- for -logit- is overdoing 
it a bit, but it works.

--Bobby
rgutierrez@stata.com
*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index