Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Hausman's test for the two-way random effects model


From   "Kate Ivanova" <statakat@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Hausman's test for the two-way random effects model
Date   Sat, 4 Nov 2006 09:17:16 -0600

Hello,

I would like to perform Hausman's test to compare two-way fixed
effects versus two-way random effects model (that is, I have both
country and year specific effects). I estimate the models using
xtmixed but I am not sure what the correct syntax for Hausman's test
should be or whether this test can be applied to two-way models at
all.

So far, I have typed

xtmixed depvar indepvar countrydummies yeardummies
est store fixed
xtmixed depvar indepvar || _all: R.country || _all: R.year
hausman fixed

The test is perfomed and I get the chi2 value. But then I also get
"(V_b-V_B is not positive definite)."

I would appreciate any help with the correct syntax for the two-way
model or for any alterantive ways to test fixed versus random effects
in a two-way model.

Thank you very much in advance.

Kate
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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   |   What's new   |   Site index