Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: Re: st: panel with cross-sectional dependence nd endogeneity


From   [email protected]
To   [email protected]
Subject   Re: Re: st: panel with cross-sectional dependence nd endogeneity
Date   Wed, 26 Sep 2007 12:53:40 +0200

I use Stata 9.2
You can just add the robust option after the comma: xtreg y x, robut. 
On Statalist, we have some "rules" (see the FAQ): Stata commands should be cited between dashes - - 
You can download -xtscc- by typing ssc install xtscc. Please note that -xtscc- let you have far more than robust standard errors (but not random effects).
Nicola

At 02.33 25/09/2007 -0400, Jasminka wrote:
>Quoting [email protected]:
>
>hi Nicola,
>
>it seems that your answer is usefull for me, too. namely, I asked about 
>how to estimate random effects with robust errors. the question still 
>stays: which Stata version are you using? I can not find command xtscc 
>in my 9.2 version. and what about dashes? could you, please, clarify?
>
>thank you so much.
>Jasminka
>
>> -xtscc- (remember the dashes!) is useful for both cross-sectional 
>> dependence and heteroskedasticity, while fixed effects (it's one of 
>> the two options) allows for endogeneity
>> Nicola
>> At 02.33 21/09/2007 -0400, "Ivan Etzo" wrote:
>>> Dear All,
>>>
>>> my panel (N=3D2660 ; T=3D7) presents either heteroskedasticity = 
>>> (lrtest and xttest3) endogeneity and cross-sectional dependence 
>>> (xtc= sd test). Moreover there is also serial correlation (xtserial 
>>> test).
>>> Thank to statalist I found useful commands to correct my analysis 
>>> bu= t I haven't found a way to cope with all of them together yet.&=
>>> nbsp;The command xtscc for ex. is useful for the cross-sectional 
>>> dependen= ce (nd maybe also heteroskedasticity..?) but not in the 
>>> case of endogenou= s covariates. For the endogeneity problem, I 
>>> tried different commands lik= e ivreg2 and xthtaylor, the last one 
>>> give nice results in terms of expect= ed coeff signs and their 
>>> significance, but they don't provide correct SE = for cross-sect 
>>> dependence. Xtgls seems good for heteroskedasticity (= and serial 
>>> correlation) but not for endogeneity.
>>> I can say that I'm new with empirical analysis and panel data so 
>>> eve= ry suggestion or comment would be pretty appreciated.
>>>
>>> thanks to all
>>>
>>> Ivan 
*
*   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/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index