Johan,
Thanks really for comment. But still I am not sure whether mfx is the
right command to use after gllamm to get marginal effects. As you said, it
is possible to get "eform" of the coeffcients, which are practically the
same with the orginal gllamm result. But what is the use of mfx as long as
the coeffcients are the same, this is my problem. I belive their must be
other option to get marginal effects after gllamm for ordered probit link,
with six outcomes in my case.
With best regards
million
Mayten,
>
> Unless using 'eform' option when estimating the model Gllamm is reporting
> the marginal estimates and confidence intervals, that is the same results
> you get with mfx (or mfx2) after gllamm.
>
> If you want the exponentiated estimates and confidence intervals after
> estimating the model type: gllamm, eform
>
>
> /Johan Hellstrom
>
> *
> * 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/
>
*
* 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/
