RE: st: RE: xtgls, p(h) versus xtreg, re robust cluster()

["Schaffer, Mark E" <M.E.Schaffer@hw.ac.uk>]

Vincenzo,

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> Vincenzo Lombardo
> Sent: Wednesday, August 09, 2006 12:10 PM
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: RE: xtgls, p(h) versus xtreg, re robust cluster()
> 
> thanks mark,
> i gave a look at the FAQ's, but they refer to the difference 
> between xtgls and OLS with robust cluster() option...
> i had a doubt related to the difference between xtgls, p(h) 
> and Random effect estimator with the robust cluster option...
> is there any difference? that is..

I think the point is that xtgls is naturally compared to regress because
it isn't a fixed or random effects estimator.  Thus in the simple
homoskedastic, no autocorrelation case,

webuse abdata
xtgls n w k
regress n w k

xtgls and regress generate the same coefficients and almost identical
SEs.

HTH.

Cheers,
Mark

> is there any difference between running xtgls, p(h) and 
> xtreg, re robust cluster()??
> thanks a lot...
> 
> In data Wed, 09 Aug 2006 12:04:16 +0100, Schaffer, Mark E 
> <M.E.Schaffer@hw.ac.uk> ha scritto:
> 
> > Vincenzo,
> >
> >> -----Original Message-----
> >> From: owner-statalist@hsphsun2.harvard.edu
> >> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> Vincenzo 
> >> Lombardo
> >> Sent: Wednesday, August 09, 2006 10:47 AM
> >> To: statalist@hsphsun2.harvard.edu
> >> Subject: st: xtgls, p(h) versus xtreg, re robust cluster()
> >>
> >> dear all,
> >> i am using panel data; i have a question on gls and robust 
> command. 
> >> do you know what is the difference between using xtgls, p(hetero), 
> >> that is groupwise heteroskedasticity, and using xtreg, re 
> robust with 
> >> or without the cluster() option?
> >
> > You might want to check the FAQs.  The following one is 
> helpful and I 
> > think indirectly answers your question:
> >
> > http://stata.co.uk/support/faqs/stat/xtgls_rob.html
> >
> > --Mark
> >
> > Prof. Mark E. Schaffer
> > Director
> > Centre for Economic Reform and Transformation Department of 
> Economics 
> > School of Management & Languages Heriot-Watt University 
> Edinburgh EH14 
> > 4AS  UK
> > 44-131-451-3494 direct
> > 44-131-451-3296 fax
> > http://www.sml.hw.ac.uk/cert
> >
> >> In both case, the estimator used should be the GLS, but I do not 
> >> understand what is the difference between using the two different 
> >> commands (xtgls, p(h) or xtreg, re robust).
> >> the coefficients given by the two approaches, indeed, results 
> >> different, sometimes only slightly, but most of the time the 
> >> difference quite substantial.
> >> thanks a lot..
> >>
> >> --
> >> Vincenzo Lombardo
> >> University of Sussex, Dept. of Economics University of Napoli 
> >> Parthenope, DSE
> >> 12 Canfield Road
> >> BN2 4DN Brighton - UK
> >> tel. (UK):++44(0)7765991711
> >> tel. (ITALY):++393284164302
> >> *
> >> *   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/
> 
> 
> 
> --
> Vincenzo Lombardo
> University of Sussex, Dept. of Economics University of Napoli 
> Parthenope, DSE
> 12 Canfield Road
> BN2 4DN Brighton - UK
> tel. (UK):++44(0)7765991711
> tel. (ITALY):++393284164302
> *
> *   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/