Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Re: st: R: st: Re: st: "cluster(firm)” vs “vce(cluster firm)”
From
"Julia Ke" <[email protected]>
To
[email protected], [email protected]
Subject
st: Re: st: R: st: Re: st: "cluster(firm)” vs “vce(cluster firm)”
Date
Tue, 27 Nov 2012 15:30:15 +0100
Dear Austin and Francesco,
Many thanks for your input.
@ Francesco: I read Petersen's 2009 paper, so gladly I seem to be on the right track. Thanks!
@ Austin: Thanks for the ivreg2 suggestion. I will definitely take a look at that too.
Best regards,
Julia
-------- Original-Nachricht --------
> Datum: Mon, 26 Nov 2012 23:51:53 +0000
> Von: "Francesco Mazzi" <[email protected]>
> An: [email protected]
> Betreff: st: R: st: Re: st: "cluster(firm)” vs “vce(cluster firm)”
> I agree with Austin.
> You should consider using cluster2.
> try googling 'petersen cluster2'
> Good luck with your research.
>
>
> Inviato dal mio smartphone BlackBerry®
> www.blackberry.com
>
> -----Original Message-----
> From: Austin Nichols <[email protected]>
> Sender: [email protected]
> Date: Mon, 26 Nov 2012 23:01:13
> To: <[email protected]>
> Reply-To: [email protected]
> Subject: st: Re: st: "cluster(firm)” vs “vce(cluster firm)”
>
> Julia Ke <[email protected]>:
> There is no difference--you also get the same results from -robust-
> options using -xtreg-.
> . xtset country
> . xtreg y x1 x2 x3 x4 x5 i.year, fe r
> See also two-dimensional clustering and other options in SSC package
> -ivreg2-:
> http://fmwww.bc.edu/repec/bocode/i/ivreg2.html
>
> On Mon, Nov 26, 2012 at 10:48 PM, Julia Ke <[email protected]> wrote:
> > Hi Statalist,
> >
> > I am working on a panel data analysis whereby I use a country and time
> fixed effect and cluster by firm (panel).
> > My question concerns the clustering. The basic model I am using is of
> the form
> >
> > Xi: regress y x1 x2 x3 x4 x5 i.country i.year
> >
> > For the clustering, I am trying to understand the difference between
> adding “,cluster(firm)” and “vce(cluster firm)”.
> >
> > Is there anything else I should pay special attention to?
> >
> > Many thanks!
> >
> > Julia
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/faqs/resources/statalist-faq/
> * http://www.ats.ucla.edu/stat/stata/
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/faqs/resources/statalist-faq/
> * http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/