Bookmark and Share

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]

Antwort: Re: Antwort: RE: st: Direction of the effect of the cluster command on the standard error depends on the inclusion of a control variable


From   Justina Fischer <JFischer@diw.de>
To   statalist@hsphsun2.harvard.edu
Subject   Antwort: Re: Antwort: RE: st: Direction of the effect of the cluster command on the standard error depends on the inclusion of a control variable
Date   Thu, 6 Jan 2011 17:06:04 +0100

Austin -
I recall some very old posting (prior to your empirical testing) where we spoke of 100 clusters needed  for the asymptotics to kick in.
Particularly when clustering at the country level requiring a large number of clusters could become a problem, so I am really interested in your future findings for non-linear models...
Best
Justina


-----owner-statalist@hsphsun2.harvard.edu schrieb: -----

An: statalist@hsphsun2.harvard.edu
Von: Austin Nichols <austinnichols@gmail.com>
Gesendet von: owner-statalist@hsphsun2.harvard.edu
Datum: 06.01.2011 02:43PM
Thema: Re: Antwort: RE: st: Direction of the effect of the cluster command on the standard error depends on the inclusion of a control variable

Eric-
Those should be the same file, but I guess one got corrupted--thanks
for the heads-up.
Justina-
Of course the CRSE has different properties in a nonlinear model, but
I suspect the same intuition applies with slightly larger minimum
numbers of clusters.  I have not run the relevant simulations, though.

On Thu, Jan 6, 2011 at 7:51 AM, DE SOUZA Eric
<eric.de_souza@coleurope.eu> wrote:
> The one at this address opens without problem:
> repec.org/usug2007/crse.pdf
>
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Neil Shephard
> Sent: 06 January 2011 13:21
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: Antwort: RE: st: Direction of the effect of the cluster command on the standard error depends on the inclusion of a control variable
>
> On Thu, Jan 6, 2011 at 12:12 PM, DE SOUZA Eric <eric.de_souza@coleurope.eu> wrote:
>> I did download and save, then open with Acrobat Pro I did this in the
>> past, too In between I have switched from WinXP to Win7 and also have
>> a new version of Acrobat.
>
> I too have problems viewing the PDF after downloading using Adobe Acrobat 9.4.1 under GNU/Linux.
>
> Neil

> *
> *   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/
>

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index