Re: st: Which output is best for ordered logit?

[Johanna Avato <johanna.avato@googlemail.com>]

Thanks, that is a good suggestion.
Still, I will also have to come up with output tables, what would you  
use, odds or marginal effects?

On Jan 15, 2009, at 11:21 AM, Ulrich Kohler wrote:

> Am Donnerstag, den 15.01.2009, 10:26 -0500 schrieb Johanna Avato:
> > I am running an ordered logit model with 3 categories. I am wondering
> > if it is better to report the proportional odds ratios (or their
> > percentage change) or the marginal effects for each outcome. Any
> > suggestions? Usually, I like the marginal effects but I find them  
> > less
> > intuitive when the sign is actually changing across the outcome
> > categories.
>
> I would use plots to show the results of order logit models.  Take a
> look at  Long/Freese (2006: 211).
>
> @BOOK{long06,
>  author = {Long, J. Scott and Freese, Jeremy},
>  year = {2006},
>  title = {Regression Models for Categorical Dependent Variables Using
> Stata},
>  address = {College Station},
>  publisher = {Stata Press},
>  edition = {2}
> }
>
>
> --
> kohler@wzb.eu
> 030 25491-361
>
> *
> *   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/

*
*   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/