Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Re: st: Clustered standard errors: Insufficient observations


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: Re: st: Clustered standard errors: Insufficient observations
Date   Sat, 14 May 2011 13:55:38 -0500

On Sat, May 14, 2011 at 1:45 PM, Jost Heckemeyer <Heckemeyer@zew.de> wrote:
> The "generally recommened" referred to the example I gave, i.e. I have
> cross-country data where several 100s and 1000s of firms are clustered
> within several dozens of countries, so clustering and the country level
> would indeed make sense, as you write it, Stas.  Still, it does not work
> although and I cannot see any reason why it doesn t.

The technical reason is that your degrees of freedom is the number of
clusters. If you have fixed effects, you consume all of these degrees
of freedom just by the fixed effects/country dummies, and you don't
have anything left to produce standard errors on your coefficients of
interest.

-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.

*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index