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]

st: IVREG2 and Standard Errors when Number of Clusters is Small


From   Jessie C <jessiecoh@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: IVREG2 and Standard Errors when Number of Clusters is Small
Date   Sun, 29 Jan 2012 10:58:29 -0500

In this presentation by Colin Cameron:
http://www.stata.com/meeting/mexico11/materials/cameron.pdf

it is suggested to compute the t-statistic based on G-1 or G-K-1
degrees of freedom.  I cannot quite tell which.  G is the number of
clusters.  K is the number of regressors that are grouped that bring
about the Moulton problem.

Nevertheless, I cannot quite discern which paper Cameron is referring
to that recommends this.

Is it Donald and Lang (2007)?  Looking at that paper suggests
averaging and aggregating micro-level data.  My data is already at the
country level so I'm not sure if that is relevant.

Is it Bester, Conley, and Hansen?

Is it a different one?

Thank you very much for any help you can provide.
*
*   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