Statalist


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

Re: st: RE: HUGE Wald test statistics of testing multiple coefficients in a fixed effect model with cluster option


From   "Austin Nichols" <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: RE: HUGE Wald test statistics of testing multiple coefficients in a fixed effect model with cluster option
Date   Mon, 10 Mar 2008 16:29:03 -0400

Jay--
The poster has 500 FE plus 300 dichotomous explanatory variables.  I
would guess the assumptions of RE are not satisfied, but -hausman-
might say more.

On Mon, Mar 10, 2008 at 3:48 PM, Verkuilen, Jay <JVerkuilen@gc.cuny.edu> wrote:
> [snip]
>
> >One solution is to test if I need the cluster option using the not yet
> available xtcltest (Mark and Austion, when is this program available?).
> If I do need the cluster option, the next option is to get rid of some
> of the dummy variables.<
>
> Have you considered random effects? 300 fixed effects is A LOT and I
> would suppose you have some kind of "superpopulation" in mind.
>
> Jay
*
*   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