Margit Averdijk <[email protected]> asks:
> Is obs just a third level? I xtset the data on panelvar (id) and timevar;
> should I also somehow include obs? I would like to also include random
> effects for id and age. How do I then include obs? As separate random
> intercept, like
> > . xtmepoisson ... || id: age || obs:, ...
> or a random slope?
You fit the model as a random intercept at the obs (third) level, just as you
have typed above. Then, the variance component labeled as "sd(_cons)" or
"var(_cons)" under the "obs:" part of the table estimates the overdispersion.
Also note that, unlike the other xt commands, -xtmixed-, -xtmelogit-, and
-xtmepoisson- pay no attention to settings that are -xtset-. These three
commands determine the multilevel panels entirely from their syntax.
--Bobby
[email protected]
*
* 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/
