On Feb 13, 2012, at 1:01 PM, francogrex wrote:
> Hi, in R there is the function "density" which computes kernel
density
> estimates. Is there a "cumulative" version of it? Something like
> they have
> in Matlab:
I'm not aware of one, but you could use `integrate`. You will need to
limit your range or use the version in package logspline if your
range is fixed. You will also need to account for the fact that the
inteegral will only be approximately == 1. Searching the Archives will
bring up several similar questions from prior years.\> http://www.mathworks.nl/help/toolbox/stats/ksdensity.html
> I know there is ecdf, but I'm not sure it's based on kernel density
> smoothing. Thanks
`ecdf` is not based on density.
--
David Winsemius, MD
West Hartford, CT