Trivedi covers possible specifications here:
http://fmwww.bc.edu/repec/msug2010/mex10sug_trivedi.pdf
The Wooldridge approach on slide 61 can be implemented using a dynamic poisson RE model (xtpoisson) including a lagged dependent variable and a linear projection of the original unobserved effect on x-bar and the initial condition. The other approaches are implemented using GMM.
****************************************************
Daniel L. Millimet, Professor
Department of Economics
Box 0496
SMU
Dallas, TX 75275-0496
phone: 214.768.3269
fax: 214.768.1821
web: http://faculty.smu.edu/millimet
****************************************************
-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Robert Fornango
Sent: Monday, November 26, 2012 3:28 PM
To: Statalist
Subject: st: Dynamic panel model for count data?
Dear Stata users:
I would like to estimate a dynamic panel model, such as that performed by
-xtabond2- or -xtdpdsys-, with potentially endogenous regressors. However, my dependent variable is a non-negative count that exhibits over-dispersion.
My sample consists of approximately 75 units, observed over 8 time periods (after losing 2 time periods to lags).
I am wondering if anyone knows of a Stata routine to estimate such a model?
Any advice will be greatly appreciated.
Robert J Fornango, PhD
Chief Executive Officer
F1 Analytics LLC
www.f1analytics.com
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/
