Dear xtmelogit experts:
I want to conduct a Mean-comparison test of the predicted probabilities as
generated by predict after xtmelogit estimation, something along the
following lines (using an example by Maarten) :
***begin example***
webuse bangladesh
xtmelogit c_use urban age child* || district: urban, covariance(unstructured)
predict foo
sum foo
ttest foo, by(urban)
***end example***
Is it right?
--
Sergio
*
* 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/
