Re: st: Literature Reference for Stata's Fixed-Effects Transformation

["Sebastian van Baal" <s.vanbaal@arcor.de>]

Dear Conor and Martin: 

Thank you very much for your suggestions! I was unclear in stating my
problem: I am looking for a literature reference that explains why it is
possible to add the grand mean back in if the goal is to estimate a model
constant. Virtually all the econometrics text books I looked at (now
including Stock/Watson) state that the individual mean can be subtracted for
fixed-effects transformation. But no source I have so far includes the
adding-the-grand-mean-back-in step. Stata performs this "second step" and I
understand it, but I need a reference for formal reasons and to gain a
deeper understanding of the intricacies of estimating the model constant. 

I am almost sure that the Stata programmers did rely on some scientific
source when implementing this second step. I am looking for such a source. 

Any other suggestions? 

Thanks in advance, 
Sebastian

*
*   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/