--- Jared DeLisle <[email protected]> wrote:
> Thanks for your reply, Johan. Gibbons, Ross, & Shanken (1989) show
> that using a Wald chi-square statistic to test the joint hypothesis
> that all intercepts equal zero can lead to over-rejection of the
> null (Type I error).
These finite sample corrections typically only have a noticeable
influence in very small dataset or when you are testing a huge amount
of paramters. In either case the test is suspect anyhow.
-- Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room N515
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
*
* 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/
