Belated suggestion: move to -xtscc- (can be downloaded from SSC)
Nicola
P.S. I'll NOT receive/read any email but the digest.
At 02.33 16/09/2008 -0400, you wrote:
>Hi Chandra,
>I had the same problem; i opted finally to use individual clustering
>with robust option. The clustering should be ok for autocorrelation.
>I am not sure that i am right, but it was the only way for me to
>resolve the dilemma.
>i hope that would be useful.
>Hanene
>
>2008/9/15 Chandra Kiran <[email protected]>:
>> Hi,
>> I have a question concerning estimation of a fixed-effects panel data model
>> with both heteroscedasticity as well as auto-correlation. After exploring
>> both xtgls and xtregar options, I feel both to be unsuited, since in the
>> xtregar case, one is limited to no heteroscedasticity, while in xtgls, there
>> does not appear to be the option of estimating fixed effects.
>> Can anyone suggest a specific command (or user written program) for taking
>> care of both issues in a fixed effects setting ?
>>
>> Chandra
*
* 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/
