Shuaizhang Feng wrote:
> Can anyone tell me why after xtlogit fe (fixed
> effects) the "mfx compute, predict(p)" doesn't work?
>
> The predict (p) option is what's suggested in the
> mannual. But it always gives "no effect" as the
> answer.
Try -mfx compute, predict (pu0)-. This query was covered in full only a
couple of weeks ago by two postings from May Boggess:
http://www.stata.com/statalist/archive/2004-07/msg00292.html
http://www.stata.com/statalist/archive/2004-07/msg00317.html
In it, she makes two important points:
(1) -xtlogit, fe- is algebraically equivalent to -clogit-; and
(2) there are many myriad ways to calculate marginal effects, not all of
them suitable for your own purposes.
I hope this helps.
CLIVE NICHOLAS |t: 0(044)191 222 5969
Politics |e: [email protected]
Newcastle University |http://www.ncl.ac.uk/geps
*
* 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/
