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: gologit2 model
From
Richard Williams <[email protected]>
To
[email protected], [email protected]
Subject
Re: st: gologit2 model
Date
Wed, 13 Oct 2010 13:24:41 -0500
At 12:14 PM 10/13/2010, Maarten buis wrote:
--- On Wed, 13/10/10, Nilam Prasai wrote:
> I am trying to estimate a generalized ordinal logistic
> model by using gologit2 program in stata. I have approximately 40
> observations for which predicted probability is negative. Should I be
> concernde. My sample size is 115.
Sounds like too many negative predictions to me. Rich Williams, the
author of -gologit2-, maintains an FAQ which has an entry on negative
predicted probabilities and a possible solution:
<http://www.nd.edu/~rwilliam/gologit2/tsfaq.html>
I agree with Maarten. See the FAQ. You may be able to tweak the
data or the model. However, 115 is a pretty small N for any maximum
likelihood analysis, let alone one that estimates as many parameters
as gologit2. You can also see the main support page at
http://www.nd.edu/~rwilliam/gologit2/index.html
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* 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/