Bookmark and Share

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: Hausman test


From   Christopher Baum <kit.baum@bc.edu>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   re:st: Hausman test
Date   Tue, 3 Jan 2012 10:32:23 -0500

<>
Ricardo said

I am interested in modeling cholesterol and because of the correlation within families I used -xtreg, re- (GLS) regression. However when use a Hausman test to compare the fitted model with a -xtreg, fe - model, I get p=0.00024. 

My understanding is that I should not use the random effects model, but should be using the fixed effect. What is the implication if I ignore the Hausman test and report results from the random efects model?



According to the verdict of the Hausman test, your included regressors in the RE model cannot possibly be considered independent of the random effects. Thus the coefficients on those regressors are biased and inconsistent, and the RE estimates should be trashed.

Kit

Research Papers in Economics (RePEc)
http://repec.org


*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index