Here are 2 approaches: Use logspline density estimates (logspline package) rather than kernel density estimates, this can give you a function to pass to integrate or other tools, the estimates may be a little different from the kernel density estimates.
If you need to use kernel density estimates, then realize that the kde is just the sum of 1/n times the kernel centered at each of the n points. And the integral of a sum is the sum of the integrals (and the 1/n can be factored out), so you can just integrate each of the n kernals (centered at the datapoints with proper width), then sum and divide by n (or take the mean). On Tue, Jun 26, 2012 at 6:13 PM, pilaw <pilawsk...@gmail.com> wrote: > Hello, > > I need density function so that I can find expected value (using > integration). I use density(): > f= density(data) > but f isn't a function and I can't get values and integrate it > This is very urget, so please help. > > Greetings > Peter > > -- > View this message in context: > http://r.789695.n4.nabble.com/density-function-tp4634563.html > Sent from the R help mailing list archive at Nabble.com. > > ______________________________________________ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. -- Gregory (Greg) L. Snow Ph.D. 538...@gmail.com ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
