Richard said
Am I correct in saying that -estat imtest- is White's general test,
or something like that? If I don't have any strong theory about the
form of hetero, would it make sense just to do -estat hettest- and
-estat imtest- routinely?
With the white option it is. The White test is just a special case of
Breusch-Pagan with a particular choice of -varlist-. -imtest- without
the -white- option is a broader test, due to Cameron and Trivedi,
which examines 2d-4th moments of the error distribution as I
understand it. White, Breusch-Pagan, -robvar-, Goldfled-Quandt all
just consider 2d moment.
Kit Baum, Boston College Economics
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/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
