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.

# st: RE: panel data fixed vs random

 From PIETRO MASCI To statalist Subject st: RE: panel data fixed vs random Date Sat, 2 Feb 2013 11:09:43 -0500

```Hi

i am using a panel data and run fixed effects and stored and random effects and stored to perform the hausman test.
when i use
hausman fix random
i get the following output:

Note: the rank of the differenced variance matrix (2) does not equal the number of coefficients
being tested (4); be sure this is what you expect, or there may be problems computing
the test.  Examine the output of your estimators for anything unexpected and possibly
consider scaling your variables so that the coefficients are on a similar scale.

---- Coefficients ----
|      (b)          (B)            (b-B)     sqrt(diag(V_b-V_B))
|      fix         random       Difference          S.E.
-------------+----------------------------------------------------------------
Penetratio~2 |   -83456.95    -29177.79       -54279.16               .
GastosSaud~a |    .6067533    -4.087394        4.694147               .
MortHomicp~b |     4.54167     65.12774       -60.58607               .
interinsfi~a |     .238441     .3677846       -.1293436               .
------------------------------------------------------------------------------
b = consistent under Ho and Ha; obtained from xtreg
B = inconsistent under Ha, efficient under Ho; obtained from xtreg

Test:  Ho:  difference in coefficients not systematic

chi2(2) = (b-B)'[(V_b-V_B)^(-1)](b-B)
=    -5.80    chi2<0 ==> model fitted on these
data fails to meet the asymptotic
assumptions of the Hausman test;
see suest for a generalized test

If i run the hausman test in the reverse order:

hausman random fix

i get the following output:

Note: the rank of the differenced variance matrix (2) does not equal the number of coefficients
being tested (4); be sure this is what you expect, or there may be problems computing
the test.  Examine the output of your estimators for anything unexpected and possibly
consider scaling your variables so that the coefficients are on a similar scale.

---- Coefficients ----
|      (b)          (B)            (b-B)     sqrt(diag(V_b-V_B))
|     random        fix         Difference          S.E.
-------------+----------------------------------------------------------------
Penetratio~2 |   -29177.79    -83456.95        54279.16        56513.77
GastosSaud~a |   -4.087394     .6067533       -4.694147        2.920822
MortHomicp~b |    65.12774      4.54167        60.58607        31.10263
interinsfi~a |    .3677846      .238441        .1293436        .0192787
------------------------------------------------------------------------------
b = consistent under Ho and Ha; obtained from xtreg
B = inconsistent under Ha, efficient under Ho; obtained from xtreg

Test:  Ho:  difference in coefficients not systematic

chi2(2) = (b-B)'[(V_b-V_B)^(-1)](b-B)
=        5.80
Prob>chi2 =      0.0552.

How do i interpret the test?
should i reject the fixed effects based on the chisquare of the second output (5.8;0.055)?
should i transform/scale the variables? use log?

thanks a lot!

Pietro Masci
pete888888@msn.com
*
*   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/
```