I don't understand what you mean by unweighted and weighted here.
Nonparametric regression is, in my understanding, aleays some kind of
weighted local combination of response given predictor: that is the
whole point of the exercise.
Otherwise, yes: in Stata 10 this sounds like -lpoly- (formerly
-locpoly-) with -kernel(rectangle)-.
Nick
[email protected]
xinzheng shi
I would like to get a prediction from unweighted
uniform kernel smoother. In STATA, it seems "locpoly"
is the one to do this kind of nonparametric
regression, but it gets weighted conditional mean. I
was wandering whether there is any syntax in STATA
which could be used to get unweighted conditional
mean. Or I might understand "locpoly" wrong?
*
* 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/
