[R] qhuber-locfit: residual variance
Maciej.Hoffman-Wecker at evotecoai.com
Tue Mar 12 14:22:16 CET 2002
I've 2 questions concerning locfit, I didn't find in Loader: Local
1. If I perform locfit with family = "qhuber", the residual variance
is based on normalized residuals. "qgauss" is on original scale.
Is this a bug or is there a reason for it?
2. Is the residual variance estimate (rv) in case of a fit with family =
a robust estimate?
Thanks in advance
Screening Operations/Discovery Informatics
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch
More information about the R-help