behalf of Edzer Pebesma
Sent: Fri 6/1/2012 3:58 AM
To: r-sig-geo@r-project.org
Subject: Re: [R-sig-Geo] simulating a particular autocorrelation structure for
a raster
Erin, I believe the following would do this:
xy = expand.grid(x = 1:16, y = 1:16)
d = as.matrix(dist(xy))
sim = chol(0.9 ^ d
Erin, I believe the following would do this:
xy = expand.grid(x = 1:16, y = 1:16)
d = as.matrix(dist(xy))
sim = chol(0.9 ^ d) %*% rnorm(256)
require(sp)
grd = SpatialPointsDataFrame(SpatialPoints(xy), data.frame(sim=sim))
gridded(grd) = TRUE
spplot(grd, col.regions=bpy.colors())
I used distance
Dear R Sig Geo People:
I would like to create a 16x16 raster, say, with autocorrelation structure of
0.9 for nearest cell, 0.9^2 for 2nd closest, and so on.
How would I go about generating that, please?
I thought about putting together a correlation matrix, multiplying, and
throwing in rnorm.