< >
Maarten said
> And I am running a xtreg, re. I need to suppress the intercept.
> However Stata 10 doesn't allow this option. Is there a rationale for
> this ?
I always think of random effects a way of estimating for each group a
separate intercept in terms of a deviation from the intercept reported
in the main table by -xtreg, re-. (These intercepts aren't estimated
directly, but are represented as a distribution.) Given this way of
thinking about a random effects model, I would be very reluctant to
suppress the intercept.
The REs are random variables drawn from a distribution with a mean of
zero. If the intercept was suppressed, the mean would not necessarily
be zero, just as in OLS without a constant term, where the constraint
that the residuals sum to zero reflects the presence of the intercept
in the model.
Kit Baum, Boston College Economics and DIW Berlin
http://ideas.repec.org/e/pba1.html
An Introduction to Modern Econometrics Using Stata:
http://www.stata-press.com/books/imeus.html
*
* 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/
