There are two reasons for the difference in speed between -svyregress- and
-svy: regress-.
1. Compiled code written in C is faster than Mata, although compiled Mata
code is very fast compared to interpreted Stata code.
2. General purpose code tends to be slower than code written to take
advantage of a special case.
Thanks for the explanation Jeff. Still, speed differences of 6:1, like
Robert found, are not trivial. Hopefully Stata can do something to address
that, perhaps either by going back to C code or speeding up Mata. Any one
who doesn't need Stata 9's new features (which are very impressive) may
wish to use Stata 8.2 version control when doing svy analysis.
