Statalist The Stata Listserver


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

Re: st: stata9.0 and 9.2..clustering?


From   "Austin Nichols" <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: stata9.0 and 9.2..clustering?
Date   Tue, 29 May 2007 16:10:22 -0400

alessia matano--
Did you read -help whatsnew- as Nick advised?
You would have seen
--update 15sep2005--
(30)B.  xtreg, fe and xtreg, re produced cluster-robust VCEs when the
panels were not nested within the clusters.  In some cases this VCE is
consistent, and in others it is not.  You must now specify the new
nonest option to get a cluster-robust VCE when the panels are not
nested within the clusters.

Here is a better way to report a "problem," by the way-- use data that
is available to everyone and report exactly what you typed, without
ellipses (also as Nick and the FAQ already advise quite explicitly):

webuse grunfeld, clear
gen reg=com if t<5
replace reg=10-com if t>=5
xtreg mval inv, fe cluster(reg)
version 9.0
xtreg mval inv, fe cluster(reg)
version 9.2
xtreg mval inv, fe cluster(reg) nonest

On 5/28/07, alessia matano <alexis.rtd@gmail.com> wrote:
ok. you are right

I am using
xtreg wage ...., fe cluster(reg)
it is an official stata command, is not it?
thank you

2007/5/28, n j cox <n.j.cox@durham.ac.uk>:
> The Statalist FAQ does give the advice, etched
> into my inner being ever since I wrote the original:
>
> "Say exactly what you typed and exactly what Stata typed (or did) in
> response. N.B. exactly!"
>
> I can see nothing in your question even about what Stata commands
> you are using and whether they are official or user-written.
>
> If you read through the help for -whatsnew- you will get information
> on what has changed in official Stata since the release of Stata 9.0.
> Otherwise I suggest that more information is needed.
>
> Nick
> n.j.cox@durham.ac.uk
>
> alessia matano
>
> there is a thing really strange that is happening using either
> stata9.0 or stata 9,2.
> I am estimating a panel equation where the id is the worker, and of
> course t=year.
> I do my estimations clustering by the region where the worker works.
> (So it is possible that from one year to another the worker can change
> region of work).
> So, when I use stata 9.0 it does the estimates. When I use stata 9.2
> it says "Panels non nested within cluster".
>
> This sentence has happeared to me already in stata 9.0 but only when I
> tried to do the regression with lagged variables, so that for workers
> changing region it had sense in effect.
> What could is mean to you?
> What is that the problem?
*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index