[R] Density estimates in modelling framework

Martin Maechler maechler at stat.math.ethz.ch
Fri Aug 29 21:13:39 CEST 2008


>>>>> "hw" == hadley wickham <h.wickham at gmail.com>
>>>>>     on Fri, 29 Aug 2008 14:03:45 -0500 writes:

    hw> Hi all, Do any packages implement density estimation in
    hw> a modelling framework?  I want to be able to do
    hw> something like:

    hw> dmodel <- density(~ a + b, data = mydata)
    hw> predict(dmodel, newdata)

    hw> This isn't how sm or KernSmooth or base density
    hw> estimation works.  Are there other packages that do
    hw> density estimation?  Or is there some reason that this
    hw> is a bad idea.

I always recommend  logspline.

Martin Maechler, ETH Zurich

    hw> Hadley

    hw> -- http://had.co.nz/

    hw> ______________________________________________
    hw> R-help at r-project.org mailing list
    hw> https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do
    hw> read the posting guide
    hw> http://www.R-project.org/posting-guide.html and provide
    hw> commented, minimal, self-contained, reproducible code.



More information about the R-help mailing list