Hi everybody ....
I am ineterested in learning how to evaluate LOCALLY (and not over the
whole data set) the confidence limits of my prdicting model ( let it be
a simple linear y=f(x) model) ... knowing that the number of
observations is not large locally .
thnks in advance
--
Hedi chtourou
Professeur associe
Dept. Genie Mecanique
Universite Laval - Quebec - Canada
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
