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: RE: st: RE: Cluster standard errors by time and firm
From
Judson Caskey <[email protected]>
To
"[email protected]" <[email protected]>
Subject
RE: RE: st: RE: Cluster standard errors by time and firm
Date
Thu, 14 Jun 2012 17:47:06 -0500
I have a couple of commands posted at https://webspace.utexas.edu/jc2279/www/data.html that will perform the two-way clustering (see 'cgmreg' commands, as in Cameron, Gelbach and Miller, 2010 Jnl of Bus. and Econ. Statistics), but you do need to mind the issues that others have raised regarding the number of time periods because the clustered standard errors are consistent as the number of clusters becomes unbounded.
There are a couple of approaches you can take using the commands that I've posted. In the cgmreg command, you can put a "max" option that takes the larger of two-way clustered, White, or vanilla OLS standard errors. The cgmwildboot command uses bootstrapped p-values.
Judson Caskey
[email protected]
*
* 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/