Re: st: Basic fixed effects estimator question

[David Jacobs <jacobs.184@sociology.osu.edu>]

Maybe an easier way (although it produces much more output) is to use 
tabulate [e.g. "tabulate dm, generate(caseid)"] to generate a dummy for 
each value of your case indentifier and then use regress.  The output is 
bulky because all of the coefficients on the case dummies are reported, but 
then you can use the diagnostics available for regression like rvfplot or 
acprplot etc.  Remember as well that "areg" produces fixed effects 
estimation and robust is allowed.

Dave Jacobs

At 01:12 PM 12/17/2004 -0800, you wrote:

> Hi Stata users,
>
> I have a question about the estimator for fixed effects in
> the linear model. That is
>
> . xtreg, fe
>
> I have seen in the XT manual ( version 8, p. 207) that this
> is estimated by running OLS on:
>
> yit -yi(bar) + y (double bar) = ......
>
> I was wondering if there is an easy way to force Stata to do
> the traditional version of this estimator, that is run OLS
> on:
>
> yit - yi (bar) = ....
>
> I know that I could transform the data but I will like to
> know if Stata can do this automatically.
>
> Thanks,
> Alejandro
>
> *
> *   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/

*
*   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/