re: RE: st: areg Vs fe

[Christopher Baum <kit.baum@bc.edu>]

<>
Richard wrote

I don't think it is a matter or running a test; it is a matter of 
which is appropriate given the nature of your problem. The help for 
areg says "areg is designed for datasets with many groups, but not a 
number of groups that increases with the sample size."

Good advice indeed. Note that in

webuse grunfeld,clear
reg invest mvalue kstock i.company
xtreg invest mvalue kstock,fe
areg invest mvalue kstock, absorb(company)

The three sets of point and interval estimates are identical, as they are estimating exactly the same model.

Kit

Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                             An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.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/