[R] nonlinear least square fit of a known function

Peter Dalgaard BSA p.dalgaard at biostat.ku.dk
Fri Oct 25 16:22:11 CEST 2002


Douglas Bates <bates at stat.wisc.edu> writes:

> John Fox <jfox at mcmaster.ca> writes:
> 
> > Dear Andy and Dave,
> > 
> > The nls documentation indicates that weights aren't (yet) implemented.
> > 
> > Regards,
> >   John
> 
> But there is an example in the documentation, contributed by Martin
> Maechler, showing how to do weighted nonlinear least squares.

And of course multiplying both sides of a model formula with the
square root of the weights is not going to make the model any more nor
less nonlinear. (But predicting and such requires a little care).
Actually Martin's example is slightly different from what weights=w
would do since his weights depend on the predictor.

Still, a weights argument would be nice. Could we have one for 1.7.0?
Any inklings about how hard it would be to implement?

        -p

-- 
   O__  ---- Peter Dalgaard             Blegdamsvej 3  
  c/ /'_ --- Dept. of Biostatistics     2200 Cph. N   
 (*) \(*) -- University of Copenhagen   Denmark      Ph: (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk)             FAX: (+45) 35327907
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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 mailing list