Stata: Data Analysis and Statistical Software

                .gllamm dep_var ind_var, i(subject_id) l(probit) f(binom)
                .gllamm, robust cluster (group_id)

Or would a three level model be the better choice?

                .gllamm dep_var ind_var, i(subject_id group_id) l(probit)
f(binom)

I do not understand how I can control for time effects. Is it possible to
simply add dummies for each year or does the gllamm command already take
into account the time structure of the data? 

Thanks for your consideration,

Petra Nieken     



*
*   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/