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: p-values based on non-standard critical t-values after -xtreg, fe- and using -estout-
From
Bert Jung <[email protected]>
To
[email protected]
Subject
st: p-values based on non-standard critical t-values after -xtreg, fe- and using -estout-
Date
Fri, 7 Dec 2012 16:10:46 -0500
Dear Statalisters,
I run -xtreg, fe- regressions with a small number of clusters and
would like to adjust the critical values along the lines of Donald and
Lang (2007), using a t(G-2) distribution where G is the number of
clusters. In my case the number of clusters is constant across all
regressions at G=20.
According to Baum et al (2011) Stata uses a t(G-1) distribution to
determine critical t-values and hence the p-values. I am looking for
an efficient and transparent way to instead output p-values using
t(G-2).
I use Ben Jann's user-written -esttab- (on SSRN).
Any thoughts much welcome.
Thanks Bert
Donald SG, Lang K. Inference with Difference-in-Differences and Other
Panel Data. Review of Economics and Statistics 2007; 89; 221–233.
Baum et al 2011, "Evaluating one-way and two-way cluster-robust
covariance matrix estimates"
http://fmwww.bc.edu/repec/dsug2011/desug11_schaffer.pdf
*
* 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/