[R] Regression on non linear model

Thomas Lumley thomas@biostat.washington.edu
Thu, 14 Oct 1999 08:36:17 -0700 (PDT)


On Thu, 14 Oct 1999, Bill Venables wrote:

> One further advantage of doing it this way (in S-PLUS at least) is that you can
> plot that component of the fitted curve very simply using plot.gam.  Now I know
> we don't have a gam() in R yet, but I hope we plan to do so sometime and my
> suggestion would be to start with a plot.gam and release that first.  It could
> be done in a wet weekend (but I regret to say the weekends here are simply
> beautiful.... :-)

I have a predict(, type="terms") and also resid(,type="partial") for glms
which are the main part of these plots. I wrote it a few versions ago, so
I will probably have to update a bit. 

	-thomas


Thomas Lumley
Assistant Professor, Biostatistics
University of Washington, Seattle

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel 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-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._