Statalist The Stata Listserver

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

Re: st: Fixed Effect Estimation Results

From   "Joana Quina" <[email protected]>
To   [email protected]
Subject   Re: st: Fixed Effect Estimation Results
Date   Wed, 5 Apr 2006 18:24:29 +0100

Mark and Bill,

Thank you for your answers - they were quite helpful.  The lpop
variable does seem to be problematic. What I still have some problems
with is that excluding it actually decreases the correlation.  I have
rechecked the lpop data just to make sure there wasn't some mistake
somewhere, but it seems fine.

Thanks again,

On 05/04/06, William Gould, Stata <[email protected]> wrote:
> To rehash, Joana Quina <[email protected]> reported,
>    1.  She has estimated the parameters of a model using -xtreg, fe- and
>        that the reported correlation between u_i and X_ij*b is .9249.
>    2.  She has estimated the parameters of the same same model on
>        the same data.  She then performs a Hausman test that fails to
>        reject random effects.
> I agree with Mark Schaffer <[email protected]>, who wrote,
> > I wonder if this is being driven by the "omnibus" nature of your Hausman
> > test.  In your application, it has 12 degrees of freedom, one for each
> > coefficient.  I can imagine that, loosely speaking, if one coefficient is
> > "significantly different" between the 2 specifications, and the other 11 are
> > "very similar", then your Hausman test could fail to reject the null that
> > the specifications are both consistent.
> In Joana's case, one coefficient changed a lot.  The Hausman test is known
> to lack power in such cases.
> -- Bill
> [email protected]
> *
> *   For searches and help try:
> *
> *
> *

*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index