I've been looking for a way to correct for within-group correlation in a
time-series survey dataset (with resulting biased standard errors). The
solution I've found is to use areg with the cluster(group identifier)
and absorb(person id) options. Since areg and xtreg, fe do the same
thing (right?), why isn't cluster an option in xtreg, fe? It would have
saved me a lot of time if it had been.
Thanks,
Andy Eggers
Brookings
Washington, DC
*
* 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/
