Re: st: hierarchical linear modeling (multilevel analysis)

["Anders Alexandersson" <andersalex@gmail.com>]

Nicola <nicola.baldini2@unibo.it> wrote:
> I have 600 observations like the following:
> UNI Y X Z INV
> where [...] Y is the patent count for the professor's university (the
> dependent variable), [...]
> following the reviewer's suggestion I then focused on -gllamm-, but
> it unclear how to handle this mix between university-level and
> individual-level variables, and most important, if such mixed estimation
> is feasible or is wrong.
You may want to read up on gllamm and xtmixed and then ask a more
precise question. For example, I'm not sure if you mean fully nested
levels of random effects or crossed random effects. An excellent
tutorial on xtmixed and gllamm for multilevel mixed-effects linear
regression is the book Multilevel and Longitudinal Modeling Using
Stata by Rabe-hesketh and Skrondal which you can purchase at
http://www.stata-press.com/books/mlmus.html.

Anders Alexandersson
andersalex@gmail.com
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/