Page 1 of 1

Hausman Test help

Posted: Sun Mar 04, 2012 3:47 pm
by sxh918
I need to run a Hausman test in eviews 7 but the following error appears each time :
* Cross-section test variance is invalid. Hausman statistic set to zero.
** WARNING: robust standard errors may not be consistent with
assumptions of Hausman test variance calculation.

How do I run the Hausman test without robust standard errors?

Re: Hausman Test help

Posted: Sun Mar 04, 2012 7:53 pm
by EViews Gareth

Re: Hausman Test help

Posted: Tue Mar 06, 2012 12:03 am
by sxh918
My lecturer suggested I do the following:
1) to do the hausman test in regressions without robust standard errors 2) analyse 3) run the regressions with robust errors.

Would this work?