Hi, Leonid. In addition to -areg- as suggested by David, you
can also try -xtgls-, which allows heteroskedasticity across
panels and/or AR(1) autocorrelation. -xtgls- uses different
assumption than _robust (Huber/White/Sandwich model in
Stata), but both take care of the panel-heteroskedastic
issue. You can check out here to see if it is useful to you:
http://www.stata.com/support/faqs/stat/xtgls_rob.html
Among all the -xt- commands, -robust- options seems
available only with -xtreg, pa- or -xtgee-. Both, however,
are population-averaged models.
---- Original message ----
>Date: Tue, 10 Jun 2003 16:48:29 -0400
>From: David Jacobs <[email protected]>
>Subject: Re: st: Robust option with panel estimations
>To: [email protected]
>
>You can use AREG with the robust option to get Huber-White
corrected
>standard errors for a fixed effects analysis.
>
>Dave Jacobs
>
>At 04:08 PM 6/10/2003 -0400, you wrote:
>>Dear all,
>>
>>Stata provides the option "robust" with reg and ivreg
commands to use
>>Huber-White estimator of variance
>>Is it possible to use the Huber-White estimator with panel
data? xtreg and
>>xtivreg do not have the "robust option"
>>
>>Thank you,
>>Leonid
>>
>>*
>>* 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/
*
* 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/
