I do not know precisely what the other packages are doing, but specifying
the -nmp- option will change the divisor used in estimating the
working-correlation matrix from N to N-p, which is the most popular
small-sample adjustment.
-- David
ddrukker@stata.com
Thanks David. The -nmp- adjustment is apparently not the adjustment
being made by SAS and SPSS, as using it does not yield the same
results. Given that SAS and SPSS think the adjustment they are doing
is good enough to make it the default, perhaps some future update of
Stata could add it as an option? It always annoys me when I can't
replicate results, because I'm not sure if I am doing something wrong
or if it is some fundamental difference in the programs.