st: RE: Cluster standard errors by time and firm

["Schaffer, Mark E" <M.E.Schaffer@hw.ac.uk>]

Sebastiaan,

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> sebas nicaise
> Sent: Monday, June 11, 2012 1:49 PM
> To: statalist@hsphsun2.harvard.edu
> Subject: st: Cluster standard errors by time and firm
> 
> 
> Dear all,
>  
> I have an unbalanced panel data set and I want to perform 
> several regressions.
> The problem is that I have overlapping observations in my 
> dependent variable meaning that I have mechanical serial 
> correlation in that variable.
> Therefore, I want to cluster my standard errors by firm and 
> time ( quarter).
> I have only been able to cluster my variable by firm.
> Is this possible in stata, and how would I do this?

The cluster-robust covariance estimator is robust to arbitrary
within-cluster (serial) correlation, so it's not clear you need anything
more than that for the VCV and SEs.  But if you tell us more about your
problem and your dataset - e.g., is it a large-N or/and large-T panel,
what version of Stata you're using, what other features your model has -
perhaps someone can offer some other suggestions.

HTH,
Mark

>  
> Thank you,
> Sebastiaan 		 	   		  
> *
> *   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/
> 


-- 
Heriot-Watt University is the Sunday Times
Scottish University of the Year 2011-2012

Heriot-Watt University is a Scottish charity
registered under charity number SC000278.


*
*   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/