[R] Density estimation
Greg.Snow at imail.org
Wed Apr 23 17:47:20 CEST 2008
Look at the logspline package. It has a different way of estimating
densities that allows for limits to be specified (i.e. probability is 0
beyond the point(s) you specify).
Hope this helps,
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
greg.snow at imail.org
> -----Original Message-----
> From: r-help-bounces at r-project.org
> [mailto:r-help-bounces at r-project.org] On Behalf Of Gunther Jansen
> Sent: Wednesday, April 23, 2008 4:59 AM
> To: r-help at r-project.org
> Subject: [R] Density estimation
> I am analysing a dataset containing genetic distances within
> and between species. I want to show a overlap of the
> distributions of the intra- and interspecific values; on a
> second graph I use a cut-off value to determine these
> boundaries. As the dataset contains >30 000 values, I would
> like to do this with a simple line rather than superimposed
> histograms. Hence, density plots. With the standard settings
> of plot(density(x)), I receive the desirable result, except
> that the function extends slightly in negative x values
> (which is impossible, distance values are always positive).
> Furthermore, in the second figure I supplied the cut-off
> value a priori, so overlap between the two classes is zero by
> definition. Is there a way to visualise this information in
> another way, or to readjust the density parameters so
> intraspecific values below zero have zero probability in the
> first case, and there is no overlap in the second case?
> R-help at r-project.org mailing list
> PLEASE do read the posting guide
> and provide commented, minimal, self-contained, reproducible code.
More information about the R-help