Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: testing for overdispersion in panel count data models

From   "Scott Imberman" <>
To   <>
Subject   st: testing for overdispersion in panel count data models
Date   Wed, 02 Aug 2006 10:42:08 -0400

Dear All,
I am trying to run a count data model on individual level panel data. 
I was wondering if there is any way to test whether i have
overdispersion, in which case i would use xtnbreg, fe whereas otherwise
i would use xtpoisson, fe.  I know that there is not one built into
stata, thus i was wondering if there is a user-written program that does
it or if there is some manual way to do it (i.e. through an lr test of
the poisson vs. nbreg models?)
Also, I know that this has been addressed in the archives, but not
recently.  Thus, I was wonderng if anyone is aware of any user-written
programs that add a robust standard error ability to xtpoisson and
xtnbreg?  Thanks.
Scott Andrew Imberman
Ph.D. Candidate in Economics
University of Maryland
3105 Tydings Hall
College Park, MD 20742
Voice: (301) 405-3493
Fax: (301) 405-3542 

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index