I am rather confused with the way that mfx calculates standard errors
(confidence interval) for marginal effects, especially for the nonlinear
ones (like predicted probabilities). I couln't get very explicit formula
from the help file, or the ado file per se. Any input? Thanks a lot.
Mike
_________________________________________________________________
Join the world�s largest e-mail service with MSN Hotmail.
http://www.hotmail.com
