I am using R 2.6.1 on a 64 bit PC running Windows XP Pro.
My main problem is that I want to produce a scatter plot with density
estimation, where the colors of points correspond to a kernel density estimate
at the location of the points. I have not found a package that will do this.
If there is no package, one option would to estimate the bivariate density
first, and then use it to define a color table for the points.
If I obtain a bivariate kernel density for X and Y coordinates as follows:
require(MASS)
x.coord <- rnorm(1000)
y.coord <- rnorm(1000)
kernel <- kde2d(x.coord, y.coord, n = 100)
par(mfrow=c(2, 1))
image(kernel)
points(x.coord, y.coord)
plot(x.coord, y.coord, main="I want to color these points using the kernel
density")
how can I extract the kernel density estimates at the x.coord and y.coord
locations for each point?
What I would like is a matrix with three columns for "X", "Y" and "DENSITY",
like this:
> matrix
X Y DENSITY
1 1.56 -0.03 0.05
...
Is there an easier way to do this?
Thanks in advance,
Jim
[[alternative HTML version deleted]]
______________________________________________
[email protected] 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.
