Thanks, but let me restate my question: I wanted make sure that
-xtpcse- Prais-Winsten estimator is a random effect estimator.
If it is, then is there a way to get in Stata a fixed effect estimator
that takes account of autocorrelation and heteroskedasticity?
Best,
Vladimir.
On 6/4/07, Johan Hellstrom <[email protected]> wrote:
In the manual, as well as in the output, it is showed that it is
Prais-Winsten estimates that are produced when autocorrelation is specified.
Best,
Johan Hellstrom
>Dear Statalist users and especially Stata Corp. staff,
>
>Are the coefficient estimates reported after -xtpcse, corr(ar1)- or
>-xtpcse, corr(psar1)- estimated by a RE model (namely Prais-Winsten
>GLS model)?
>
>Thanks in advance,
>Vladimir.
*
* 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/
