Re: st: slogit versus mlogit

[Richard Williams <Richard.A.Williams.5@ND.edu>]

At 12:03 PM 3/6/2006, you wrote:
> Hi
> I wonder if anyone can help me?
> I am trying to model an ordinal response variable with three levels. 
> I do not have proportional odds and so I have been investigating the 
> stereotype model. I understand that if the stereotype model is of 
> its maximum dimension, in my case 2, then the model  is equivalent 
> to a multinomial logistic regression model. Given that I believe 
> that a 2-dimensional model would be an improvement over a 
> 1-dimensional model for my data, is there any benefit in fitting the 
> model using slogit rather than mlogit? Alternatively, does anyone 
> know where I can  find detailed information on the interpretation of 
> a 2-dimensional stereotype type model from slogit, especially when 
> my explanatory variables are categorical?
> Thanks
> Sara
(Self-plug here) You may also want to take a look at -gologit2-. 
-gologit2- provides a means for estimating models that are less 
restrictive than ologit and more parsimonious than mlogit.  The 
program can be downloaded from SSC.  The support page for -gologit2-, 
which includes a pre-publication version of an article that is in the 
current Stata journal, can be found at

http://www.nd.edu/~rwilliam/gologit2/index.html


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX:    (574)288-4373
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW (personal):    http://www.nd.edu/~rwilliam
WWW (department):    http://www.nd.edu/~soc 
*
*   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/