--- On Wed, 9/9/09, Filipa de Castro wrote:
> What exactly means the option "predict(pu0)" in mfx after
> xtlogit?
> What does it imply that the random effect is fixed to 0?
In non-linear models like -logit- or -xtlogit- the marginal
effect is not constant (this is the very definition of
non-linear), but differs for different values of the
explanatory variables. To compute one number we need to fix
the values of the explanatory variables to some meaningful
number, e.g. the mean. In a random effects model like
-xtlogit- one of the "explanatory variables" is the random
variable, so we need to fix it's value to. Fixing it to 0
means that we fix it to the average value.
Hope this helps,
Maarten
--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany
http://www.maartenbuis.nl
--------------------------
*
* 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/
