Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Panel count data
From
Nick Cox <[email protected]>
To
[email protected]
Subject
Re: st: Panel count data
Date
Thu, 6 Sep 2012 18:16:27 +0100
-xtgee- seems nearer the mark for panel data.
I think you can only judge a fairly large incidence of zeros if a
Poisson family fails to account for them.
Nick
On Thu, Sep 6, 2012 at 6:07 PM, Alexander Bailey
<[email protected]> wrote:
> I have panel count data, which i have being trying to model using the
> quasi-poisson model to correct for overdispersion.
>
> glm stocklosses L.lynx L.feraldogs L.jackal L.ratelhoneybadger rain
> L.rain distance, family(poisson) link(log) scale (x2)
>
> Is this incorrect? If so what model should I use? If it is the correct
> approach how do I assess the fit of the model? Finally There is a
> fairly large incidents of zeros in my data, but stata does not allow
> me to use the zero-inflated commands with lagged explanatory variables
> which is crucial to my model.
*
* 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/