I am not sure you must. You may parametrize shape in -gnbreg- and -hcnbreg- (the latter from SSC)
P.S. I think the correct spelling is Statalist
Nicola
P.S. I'll NOT receive/read any email but the Digest.
At 02.33 13/11/2008 -0500, Glauco Peres wrote:
>Dear STATA-list,
>
>I need to run a Poisson fixed effects model.
>Before running such model, I know that I must specify both a condtional mean function and a conditional variance function.
>However, Stata does not inform the functional form it uses in such type of model.
>
>So, does anybody know what is the functional form Stata uses for conditional mean and conditional variance in a Poisson regression?
>How do I change them if a different specification better fits with data?
>
>Thanks a lot!
>
>Glauco
*
* 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/
