I'm trying to fit dynamic count data panels. My data is epidemiologycal
(number of deaths, around 20% 0's and over) with an exposure, two
continuous explicative variables, and several dummies. The series of the
independent variable is highly persistent, and this also happens with
one of the explicative variables. The data structure seems similar to
data in the literature of patents and R&D, wich is tipically fitted with
panel GMM estimators.
My questions are:
1. Is it possible to fit this kind of model with Stata 10?
2. If yes, how?
3. If not, do you have any suggestion?
I've read that there are users developing GMM routines for stata
(ivpois), but they aren't for panels.
Thanks in advance,
Fernando
--
Fernando Terres
Lecturer. PhD candidate
CERPIE/Research
Universitat Politecnica de Catalunya
Diagonal, 647 - 10
08028 Barcelona (Spain)
+34.934.010.708
[email protected]
http://cerpie.upc.edu
*
* 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/
