Rodrigo,
This is an old and quite basic Krig, my data was continuous
measurements in lat, long so binned first.
library(geoR)
counts<-bins2d(long, lat,bin=c(0.1,0.1),plot=FALSE, nlevels=15,
color.palette=heat.colors, xaxs='i', yaxs='i', las=1, main='')
countsgeo<-as.geodata(counts)
xrange<-seq(range(countsgeo$coords[,1])[1],range(countsgeo$coords[,1])
[2], by=bin[1])
yrange<-seq(range(countsgeo$coords[,2])[1],range(countsgeo$coords[,2])
[2], by=bin[2])
loci<-expand.grid(x=range(counts,y=yrange) #krig grid
kc <- krige.conv(countsgeo, loc=loci,
krige=krige.control(cov.pars=c(1, .25))) #can fine
tune
color.palette<-rainbow #use heat etc.
contour(kc,asp=1, col=col<-
c("#FFFFF",color.palette(length(levels)-1)) , add=TRUE) #makes 0
counts white
You could also use image or other 3d graphics.
Hope that Helps,
Jon Loehrke
Graduate Research Assistant
Department of Fisheries Oceanography
School for Marine Science and Technology
University of Massachusetts
200 Mill Road, Suite 325
Fairhaven, MA 02719
[EMAIL PROTECTED]
[[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.
