Re: st: use of rologit

[Phil Schumm <pschumm@uchicago.edu>]

On Aug 21, 2008, at 7:40 PM, Data Analytics Corp. wrote:
> A potential client asked for a form of analysis sometimes done in  
> market research called maximum-difference (maxdiff) analysis.  
> Basically, consumers are presented with a series of product  
> attributes (say, four at a time or a "quad") and then are asked to  
> select the one they prefer the most and the one they prefer the  
> least. For a quad, the other two non-selected attributes just fall  
> in the middle. This is repeated several times with the attributes  
> rotating following an experimental design. Since the attributes are  
> rated, I was thinking of using rologit to estimate a model. But then  
> I found a statement in the reference manual that says that "rologit  
> does not allow for other forms of incompleteness, for instance, data  
> in which respondents indicate which of four cars they like best, and  
> which one they like least, but not how they rank the two  
> intermediate cars." But this is exactly my problem. Does anyone know  
> how to trick rologit, or know of an ado file to handle this problem?

The rank ordered logit model may also be fit using -stcox-.  Allison  
and Christakis [1] show how this approach can be generalized to handle  
the types of ties you describe above.  Also, Jeroen Weesie wrote a  
Stata command many years ago called -elogit- to fit this model (try - 
findit elogit-) -- I can't recall though how he handled the subject of  
ties.


-- Phil

[1] P. D. Allison and N. A. Christakis. Logit models for sets of  
ranked items. Sociological Methodology, 24:199–228, 1994.


*
*   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/