st: re: fixed effects estimation with time invariant variables

[Kit Baum <baum@bc.edu>]

Alice said

 I reporduce
a Hausman test (fixed vs. random effect) result. How do I interpret this
result?


hausman fixed random

                 ---- Coefficients ----
             |      (b)          (B)            (b-B)
sqrt(diag(V_b-V_B))
             |     fixed        random       Difference          S.E.
------------- 
+----------------------------------------------------------------
        beta |    .0227671     .0407022       -.0179352         .023357
------------------------------------------------------------------------ 
------
                           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(1) = (b-B)'[(V_b-V_B)^(-1)](b-B)
                          =        0.59
                Prob>chi2 =      0.4426


In this case the common coefficient, beta, does not differ  
significantly between FE and RE. The Hausman test is based on the  
notion that the norm of the vector of differences between the common  
coefficients is small. In a single-coefficient case, that merely refers  
to the single difference -0.0179. That number is very large relative to  
FE or RE point estimates, but its standard error is even larger. You  
thus do not reject Ho: orthogonality of X and u, RE is the more  
efficient estimator since your Chi-square is not large enough.

Kit Baum, Boston College Economics
http://ideas.repec.org/e/pba1.html

*
*   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/