I'm using predictnl to get out-of-sample predicted
probabilities and the associated variance using
estimates from an xtprobit regression.
I am calculating the mean of these predicted
probabilities over by groups (each of which has 10
observations). I would like to calculate the standard
errors of these means. However, predictnl only gives
me the standard error (or variance) of the point
estimate, not the covariances between the predicted
values. I need the covariances to calculate the
variance of the mean.
Is there some way to calculate what I want easily in
Stata? Could nlcom do this? The alternative I've been
avoiding is to work this out by hand using the delta
method.
Here's my current code:
xtprobit poor hsize hsize2 television rechead roompp
if survey, i(clusterid)
* Predict probability of being poor and standard error
predictnl phat = predict(pu0), variance(varp)
* Calculate mean probability and mean variance by
target population, ignoring covariances
collapse (mean) phat varp, by(targetpop)
Thanks!
Gabriel
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
*
* 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/
