Re: st: Poisson or ordered logit/probit

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

At 05:35 PM 1/21/2006, Tinna wrote:
> Dear Statalisters,
>
> If my dependent variable isn't really a COUNT measure, but an ordinal
> measure of something else (in my case self assessed health status),
> can I still use the Poisson estimation? What are the cons of don't
> that? Why is e.g. ordinal logit or ordinal probit better?
>
> Thanks
> Tinna
You're not counting anything (e.g. number of times they were happy) 
so I don't think you could justify poisson.  ologit or oprobit would 
probably be most appropriate.  Or, if the assumptions of those 
methods are violated, you might try out gologit2 or mlogit or 
slogit.  Long & Freese's book is good for going over these different methods:

http://www.stata.com/bookstore/regmodcdvs.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/