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]
re:st: Re: Normality and Granger Causality in Panel Data
From
Christopher Baum <[email protected]>
To
"[email protected]" <[email protected]>
Subject
re:st: Re: Normality and Granger Causality in Panel Data
Date
Tue, 3 Apr 2012 15:17:21 -0400
<>
Chrostopher in his last email suggested that because my panel is short(T=10
and N=9) I should't use a cluster-robust estimator. However, STATA does
implemented onw automatically as you can see below the heading just above
the estimation table. is there any way to disable this??
No, in FE regression, Stock and Watson have shown that the "White" robust estimator is inconsistent for T>2. One of the ways of recovering
a consistent VCE is to use cluster-robust by panel rather than straight robust (which is equivalent to cluster-robust, every observation its
own cluster). In this case if you want to robustify the VCE, you have to use cluster-by-panel. Just don't try to do two-way clustering in this
context!
Kit
Kit Baum | Boston College Economics and DIW Berlin | http://ideas.repec.org/e/pba1.html
An Introduction to Stata Programming | http://www.stata-press.com/books/isp.html
An Introduction to Modern Econometrics Using Stata | http://www.stata-press.com/books/imeus.html
*
* 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/