Re: st: Fixed Effects Poisson Regression with Serial Correlation.

[David Jacobs <jacobs.184@sociology.osu.edu>]

How about clustering on your case identification variable?

This approach is crude and therefore inefficient because you aren't 
modeling the form taken by the serial correlation, but it should suffice.

Dave Jacobs


At 03:43 PM 4/28/2008, you wrote:

> Dear All,
>
> I have an unbalanced panel data set with 1150 panels (groups) and the
> dependent variable is a count.  The number of observations for each
> panel varies from 2 to 9.  I would like to allow or consider serial
> correlation in the error structure.   Currently, I am estimating a
> fixed effect model with "xtpoisson, fe" command.  I am wondering if
> there is any way to consider serial correlation.
>
> I sent an email earlier about estimating the model with "unstructured"
> correlation matrix.  I would really appreciate if you can tell me how
> to estimate "unconditional" fixed effect models in stata.  Is there a
> way to create the fixed effect dummies?
>
> I would really appreciate your insights on this issue.
>
> Thanks a lot!
>
> Best regards,
>
> ippab
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/