[R] Density estimates in modelling framework

hadley wickham h.wickham at gmail.com
Fri Sep 5 16:48:18 CEST 2008

Thanks for all your replies.  The suggestions I got were:

  * gss
  * logspline
  * locfit

I ended up using locfit because the interface was just right for my
needs, and it was faster than the alternatives.


On Fri, Aug 29, 2008 at 2:03 PM, hadley wickham <h.wickham at gmail.com> wrote:
> Hi all,
> Do any packages implement density estimation in a modelling framework?
>  I want to be able to do something like:
> dmodel <- density(~ a + b, data = mydata)
> predict(dmodel, newdata)
> This isn't how sm or KernSmooth or base density estimation works.  Are
> there other packages that do density estimation?  Or is there some
> reason that this is a bad idea.
> Hadley
> --
> http://had.co.nz/


More information about the R-help mailing list