Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Questions about xtsur, heteroskedasticity, and auto-correlation


From   Tirthankar Chakravarty <tirthankar.chakravarty@gmail.com>
To   Xia Zhao <xia.zhao07@gmail.com>
Subject   Re: st: Questions about xtsur, heteroskedasticity, and auto-correlation
Date   Wed, 6 Jun 2012 19:10:46 -0700

It might be possible, but Biorn does not discuss this case in the
paper cited, and -xtsur- does not account for it. You might have to
look through the literature for this generalisation to the estimator
and probably code it up yourself. Or you could write directly to the
authors of the -xtsur- package.

T

On Wed, Jun 6, 2012 at 6:46 PM, Xia Zhao <xia.zhao07@gmail.com> wrote:
> Questions about SUR, heteroskedasticity and auto-correlation
>
> Thanks a lot, Tirthankar.
>
> Is there any way to estimate SUR with heteroskedasticity and
> auto-correlation? Thanks.
>
> Sincerely,
>
> Olivia
>
> On Wed, Jun 6, 2012 at 6:17 PM, Tirthankar Chakravarty
> <tirthankar.chakravarty@gmail.com> wrote:
>> The one-way random effects model for unbalanced panels in Biorn (2004;
>> full reference in the helpfile for -xtsur- (SSC)) which is what
>> -xtsur- estimates does not account for serial correlation over time,
>> nor arbitrary individual specific heteroskedasticity other than that
>> arising from the vector of random effects.
>>
>> See the discussion in Biorn (2004) on page 283 after equation (1).
>>
>> Best,
>>
>> T
>>
>> On Wed, Jun 6, 2012 at 2:01 PM, Xia Zhao <xia.zhao07@gmail.com> wrote:
>>> Questions about xtsur, heteroskedasticity, and auto-correlation.
>>>
>>> I want to run SUR on unbalanced panel data. I just installed xtsur on
>>> my laptop.
>>>
>>> My understanding is that xtsur uses GLS to estimate the coefficients.
>>> So it can handle both heteroskedasticity and auto-correlation? Is it
>>> right?
>>>
>>> It seems that xtsur does not report R square. Do I have to calculate it myself?
>>>
>>> Thanks!!
>>>
>>> Olivia
>>> *
>>> *   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/
>>
>>
>>
>> --
>> Tirthankar Chakravarty
>> tchakravarty@ucsd.edu
>> tirthankar.chakravarty@gmail.com
>>
>> *
>> *   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/



-- 
Tirthankar Chakravarty
tchakravarty@ucsd.edu
tirthankar.chakravarty@gmail.com

*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index