st: between and fixed effects estimators

["Indradeep Ghosh" <indradeepg@hotmail.com>]

hi all
stata's online faq section makes the following claim :

suppose i have panel observations on x and y and i compute within-group 
averages of x (call this "avgx") and deviations of x from avgx (call this 
"deltax"), and i run

xtreg y avgx deltax, re ....................(1)

then the coefficient on avgx should be the between estimator (obtained by 
running "xtreg y x, be") and the coefficient on deltax should be the within 
estimator (obtained by running "xtreg y x, fe").

however, when i try (1), i get different estimators (numerically, i.e.) from 
the ones i get by using the "fe" and "be" options. has anyone encountered 
this before? if so, do you have any explanation for these differences? does 
it have anything to do with the fact that i am working with an unbalanced 
panel? many thanks.
deep


*
*   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/