On Wed, Nov 4, 2009 at 12:08 PM, Tim Waring <[email protected]> wrote:
>
> I need to fix both fixed and random effects within an ordered probit model.
> REOPROB is the package for this, and I can't believe that it would NOT have
> the facility to fit FIXED effects as well as random ones, but I can't find
> documentation on how to fit fixed effects.
Sufficient statistics may not exist. At least that is true for the
fixed-effects probit models. From [XT] Page 410:
"xtprobit fits random-effects and population-averaged probit models.
There is no command for a
conditional fixed-effects model, as there does not exist a sufficient
statistic allowing the fixed effects
to be conditioned out of the likelihood. Unconditional fixed-effects
probit models may be fit with
the probit command with indicator variables for the panels. However,
unconditional fixed-effects
estimates are biased."
See also:
http://www.stata.com/statalist/archive/2003-09/msg00103.html
Scott
*
* 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/
