[R-sig-Geo] Indicator Kriging R/gstat

[Edzer Pebesma]

Pete, for the universal kriging case I don't believe that indicator
theory allows what you want to do. See also

https://stat.ethz.ch/pipermail/r-sig-geo/2009-May/005701.html

If you disagree, could you please let me know why, or where you found
indications that this can be done?

For ordinary kriging, usually values outside [0,1] are set back to their
nearest allowed value. The degree to which they will be outside [0,1]
also depends on the variogram used -- Gaussian variograms being
notorously suspect.
--
Edzer

Pete Larson wrote:
> Hello,
>
> I would like to do indicator kriging in R/gstat. I have dichotomous
> 0/1 data and have performed ordinary kriging and universal kriging,
> but get predctions that are far from 0 and 1.
>
> Am I doing something wrong? Here is the code I have been using:
>
> #### Ordinary Kriging with krige function #####
> # ordinary kriging:
> x <- krige(z~1, ~x+y, model = v.fit, data = estand, newd = grd)
>
> ### universal block kriging:
> uk <- krige(z~x+y+DistHF+RiverDist+RiverDist2, ~x+y, model = v.fit,
> data = estand, newdata =
>       grd)
>
> Any help would be appreciated.
>
> Pete
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo

-- 
Edzer Pebesma
Institute for Geoinformatics (ifgi), University of Münster
Weseler Straße 253, 48151 Münster, Germany. Phone: +49 251
8333081, Fax: +49 251 8339763 http://ifgi.uni-muenster.de/
http://www.springer.com/978-0-387-78170-9 e.pebesma at wwu.de