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

st: RE: Two questions about ordinal regression using ologit and ocratio


From   Jon Heron <jon.heron@bristol.ac.uk>
To   statalist <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Two questions about ordinal regression using ologit and ocratio
Date   Wed, 13 Nov 2002 14:39:34 -0000

>  Hello there,
> 
> 
>  I have two *quick* questions.
> 
>  1) Am I right in thinking that ologit is the 'cumulative odds model'
>     for ordinal response variables (as described in Armstrong and Sloan,
> 1989)?



 After locating a set of manuals it appears that I am.
 Sorry about that.  Thought the help menus and web would give me
 all the same info.


 J





>  2) Is there available a generalisation of the ocratio function
>     that doesn't assume a constant slope?
>     I have a 3-level outcome and want to compare A versus B and C
>     along with B versus C.  However, I want to end up with two sets
>     of coefficients rather than the one set that ocratio will give me.
>     I have experimented with mlogit but am so far unable to have
>     two different reference groups using this method.
> 
> 
> 
*
*   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