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 on April 23, and its replacement, statalist.org is already up and running.


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

re: st: hausman test xtivreg(re) vs ivreg


From   Kit Baum <baum@bc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   re: st: hausman test xtivreg(re) vs ivreg
Date   Fri, 12 Mar 2010 11:11:03 -0500

<>
Sergio replied

Thank you Kit, the problem with a xtivreg fe model is that it drops the
variable of interest (which is the endogenous variable)

Well then the model makes no sense as an xtivreg,re. The same term which you are implicitly estimating in a FE model, encompassing all that is specific to the individual unit, appears as the random term in the RE model (it is that term which
must be uncorrelated with the error, which if you consider it endogenous it certainly is not). I can't see how a panel estimator with 
a individual-specific term (with no time variation) makes any sense. The fact that Stata will provide estimates of xtivreg, re coefficients does not imply that they have any meaning.

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