Re: st: fixed vs random effect model

[Clive Nicholas <clivelists@googlemail.com>]

Martin Weiss replied to Amatoallah Ouchen:

> The assumptions underlying the RE model are rarely fulfilled. To choose the
> model based on the pleasant answers that it gives you would be a problem for
> the referee, I guess. You must sell your choice differently...

Quite right: it's never been fulfilled in my experience; so much so
that I never bother fitting random-effects models anymore unless the
correlation between the fixed effects and the RHS covariates is zero
(or very nearly).

In addition to Hausman tests, you can check this quite easily when
running, say, FE models using -xtreg, fe-, so why haven't you?

. webuse grunfeld

. xtset company year
       panel variable:  company (strongly balanced)
        time variable:  year, 1935 to 1954

. xtreg invest mvalue kstock, i(company) fe

Fixed-effects (within) regression               Number of obs      =       200
Group variable (i): company                     Number of groups   =        10

R-sq:  within  = 0.7668                         Obs per group: min =        20
       between = 0.8194                                        avg =      20.0
       overall = 0.8060                                        max =        20

                                                F(2,188)           =    309.01
corr(u_i, Xb)  = -0.1517                        Prob > F           =    0.0000
^^^^^^^^^^^^^^^^^^^^^^^^^^
------------------------------------------------------------------------------
      invest |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
      mvalue |   .1101238   .0118567     9.29   0.000     .0867345    .1335131
      kstock |   .3100653   .0173545    17.87   0.000     .2758308    .3442999
       _cons |  -58.74393   12.45369    -4.72   0.000    -83.31086     -34.177
-------------+----------------------------------------------------------------
     sigma_u |  85.732501
     sigma_e |  52.767964
         rho |  .72525012   (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0:     F(9, 188) =    49.18              Prob > F = 0.0000

-- 
Clive Nicholas

[Please DO NOT mail me personally here, but at
<clivenicholas@hotmail.com>. Please respond to contributions I make in
a list thread here. Thanks!]

"My colleagues in the social sciences talk a great deal about
methodology. I prefer to call it style." -- Freeman J. Dyson.
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/