Clive Nicholas wrote:
> Nola Agha wrote:
>
>
>> I see here:
>>
>> http://www.stata.com/support/faqs/stat/panel.html
>>
>> some advice for testing for panel-level heteroskedasticity. Can anyone confirm
>> that the null hypothesis for the LR test is "no heteroskedasticity"?
>>
>
> Yes.
>
>
>> I actually have a dynamic panel data model. I used the above LR test without
>> the lagged dv. Does anyone know of a test for heteroskedasticity for dynamic
>> panel models?
>>
>
> -findit ivreg2-
> -findit ivhettest-
>
>
Dear Stata listers:
Actually, I also face a very similar problem.
I have dynamic panel equation like
xtabond2 growth(x) laggedvalue(x) laggedgrowth(x), ....
I want to check that dependent variable varies on x value, i.e. hetero.
Now the problem is (i) I donot need xtpcse or xtgls because they give
corrected SE, not a hetro test (ii) xtcsd says xtreg results not found
(iii) ivhettest says last estimation results not found (iv) I cannot use
LM test bcoz N>>T (as suggested in xtcsd stata article)
Is there some other solution? Your answer will be really helpfull.
Best Regards,
Tanveer
*
* 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/
