Hi. Is factorial kriging supported in any of the R packages, please? I see how to model a nested variogram, but I don't see how I could krige (predict) each component separately. It doesn't seem much more complicated than the supression of the nugget effect, though. For an example, see slides 33, 34 in [1]; more details on pages 342-349 of Chiles & Delfiner. Margaret A. Oliver Making Sense of Sensed Data Using Geostatistics <http://users.ox.ac.uk/~uauug/011105conf/Margaret.ppt>
factorial kriging, or kriging separate spatial scales based on nested variogram
2 messages · Felipe G. Nievinski, Edzer Pebesma
Felipe G. Nievinski wrote:
Hi. Is factorial kriging supported in any of the R packages, please? I see how to model a nested variogram, but I don't see how I could krige (predict) each component separately. It doesn't seem much more complicated than the supression of the nugget effect, though.
It is a bit more than that; I think it only really makes sense if you have two or more variogram components besides the nugget. It is not so hard to do, but I'm afraid none of the package developers has felt the urge to do so. Even nested variograms, e.g. with two spherical models, are afaik only found in one package, but I may be wrong there. -- Edzer
For an example, see slides 33, 34 in [1]; more details on pages 342-349 of Chiles & Delfiner. Margaret A. Oliver Making Sense of Sensed Data Using Geostatistics <http://users.ox.ac.uk/~uauug/011105conf/Margaret.ppt>
_______________________________________________ R-sig-Geo mailing list R-sig-Geo at stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/r-sig-geo