Skip to content

loess question

2 messages · Edwin Guo, Brian Ripley

#
Hi,
I used loess( ) to build a model that has 5 predictors using R of Wndows

version. And it tells me that there is an unknown error. If I decrease
the number of predictors, then there will be no error. My questions are:

1. Can loess( ) handle more than 4 predictors.
2. If it can not, is there any other smoothing regression technique that

can handle more predictors.

Any comment will be very helpful to me. Thank you in advance!


Edwin



-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
#
On Sat, 14 Apr 2001, Edwin Guo wrote:

            
Well, possibly you are short of points: you need *many* points in 4D
to do non-parametric smoothing (say billions).

You will need send us an example and the exact output to help you, though!