Re: st:about the fixed-effects model

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Tue, 31/8/10, Jing Zhou wrote:
> It is suggested that the FE model would not be appropriate
> to estimate the time-invariant variable, as such variable
> will be excluded by differencing the values. however, in my
> FE model, the time-invariant variable does not disappear and
> may be even significant. could you please advise me why it
> happens and whether I can trust this result?

There is nothing magical about the variable time that says that
time-invariant variables must dissappear in fixed effects 
regressions, but in many instances we use fixed effects 
regressions in cases where individuals/firms/countries/...
are observed over multiple time points, in which case the
time invariant variables should dissappear. 

If your dataset also is of the form individuals observed over 
time, then it means that something went wrong: either you think 
you estimated a fixed effects model but you did not, or your 
grouping variable did not identify the groups in the way you 
think it should be done, or your time invariant variable is not 
time invariant. 

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   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/