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 at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

re: st: correcting variances for Fixed Effects (within) estimator in panel data model


From   Kit Baum <baum@bc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   re: st: correcting variances for Fixed Effects (within) estimator in panel data model
Date   Wed, 14 Apr 2010 22:05:15 -0400

<>
Shuaizhang said

I am looking for technical details on how to correct variance estimates of within estimators in stata. Presumably in stata, fixed effects is calculated by within estimation (taking deviations from group means), not by adding dummies for each group separately (LSDV). But the estimated variances are not correct and need to be adjusted. I am wondering if anyone can provide me some details on how stata does this. Any references on the mechanics of this are also highly appreciated.  


All the details are contained in the Methods and Formulas section of the manual, [xt] xtreg, accessible from that hyperlink in help xtreg.

The VCE of the fixed effects estimator is computed correctly by xtreg, fe. If iid errors are assumed, the VCE is identical to that which you would get from the LSDV model. Degrees of freedom for the within estimator take account of the N means computed in the within transformation. If you request robust standard errors, Stata computes cluster-robust VCE, clustered by panel, following a recent paper by Stock and Watson (cited in the help and the manual) recommending that strategy.

Kit Baum   |   Boston College Economics & 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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index