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]
st: RE: Robust Hausman test using xtoverid
From
"Schaffer, Mark E" <[email protected]>
To
"[email protected]" <[email protected]>
Subject
st: RE: Robust Hausman test using xtoverid
Date
Wed, 29 Jan 2014 21:31:01 +0000
Ahmed,
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Abdalla, Ahmed
> Sent: 29 January 2014 18:50
> To: [email protected]
> Subject: st: Robust Hausman test using xtoverid
>
> Dear statalist
> I am comparing between a Hausman test and a robust Husman type test
> (Wooldridge 2002)
>
> ***For Hausman test, I run:
>
> xtreg ceb wtr, fe
> estimates store fixed
>
> xtreg ceb wtr, re
> estimates store random
>
> hausman fixed random //since I get Prob>chi2 =0.0000 (i.e.significant p values
> , <0.05), I use the fixed effect model.
Note that if you want to guarantee a nonnegative Hausman statistic, you should use either the sigmamore or sigmaless options, e.g.,
hausman fixed random, sigmamore
> ***For Robust Hausman test, I run:
> xtreg ceb wtr, re cluster(firmid)
> xtoverid // since since I get Prob>chi2 =0.0000 (i.e.significant p values , <0.05),
> I use the fixed effect model.
>
>
> Do I apply the xtoverid correctly here?
Yes.
> Do I have to cluster by firm if I use this robust Hausman type test ?
That's up to you! The test is as robust as you want it to be.
> Can I run
> the xtoverid without clustering as well ?
Yes. In fact, if it's a balanced panel, the statistic reported by xtoverid and no cluster or robust is numerically identical to the statistic reported by
hausman fixed random, sigmaless
See the xtoverid help file for an example.
HTH,
Mark
>
> Thanks
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/faqs/resources/statalist-faq/
> * http://www.ats.ucla.edu/stat/stata/
-----
Sunday Times Scottish University of the Year 2011-2013
Top in the UK for student experience
Fourth university in the UK and top in Scotland (National Student Survey 2012)
We invite research leaders and ambitious early career researchers to
join us in leading and driving research in key inter-disciplinary themes.
Please see www.hw.ac.uk/researchleaders for further information and how
to apply.
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/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/