Re: st: Time series Poisson regression

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

One problem using count estimators in a time-series design concerns the 
difficulty correcting count estimators for serial correlation.  I've seen 
corrections (implemented by authors) mentioned in a few journal articles, 
but I am not aware of any statistical package that does this.  In fact, 
most of the diagnostic tests for problems with time series estimation are 
not available for count estimators.  Stata does give users a Newey West 
option for count models in GLM and this step also corrects for 
heteroskedasticity, so if you have difficulties with serial correlation, 
you might try this expedient.

Dave Jacobs

At 03:34 PM 6/11/2003 -0400, you wrote:

> I am analyzing a fairly long time series incidence dataset.  The dataset
> consists of 5 year records of daily numbers of incidences in a city, which
> are believed to follow Poisson distributions.  Tobias and Campbell (1998,
> STATA sts13) model is closely related to this subject.  However, my question
> is whether it is legitimate to apply XTGEE or XTPOISSON model with only
> single independent unit (i.e., city) but a very long chain. Perhaps, there
> are better procedures to use.
>
> Thank you for your help,
>
>
> Wenjun Li, PhD
> Biostatistics Research Center
> Tufts-New England Medical Center #63
> 750 Washington Street
> Boston, MA 02111
> Tel (617) 636 1603 Fax (617) 636 5560
>
>
>
> **********************
> Confidentiality Notice
> **********************
>      The information transmitted in this e-mail is intended only for the
> person or entity to which it is addressed and may contain confidential
> and/or privileged information.  Any review, retransmission, dissemination or
> other use of or taking of any action in reliance upon this information by
> persons or entities other than the intended recipient is prohibited.
>      If you received this e-mail in error, please contact the sender and
> delete the e-mail and any attached material immediately.  Thank you.
> *
> *   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/