On 02/18/2014 06:11 PM, Moshood Agba Bakare wrote: > Dear All, > In my yield data, I have longitude and latitude as spherical coordinates > which are converted into projected coordinates - easting and northing for > variogram modelling, yield as attribute variable, and elevation. > I fitted my empirical variogram as > empvar<-variogram(yield~1,canmod.sp,cutoff=600,width=3, cressie=TRUE). > In some documents I come across, some fitted the model using easting and > northing as covariate to yield as > yield ~easting+northing rather than yield ~1. > which one do you advise me to use yield ~easting+northing or yield ~1.
If there is a strong spatial trend, general advice is to work on the residuals (~easting+northing), and use the same equation in the kriging step (universal or regression kriging). You could try both, if the difference is small, I'd suggest to not detrend (ie., use ~1) -- Edzer Pebesma Institute for Geoinformatics (ifgi), University of Münster Heisenbergstraße 2, 48149 Münster, Germany. Phone: +49 251 83 33081 http://ifgi.uni-muenster.de GPG key ID 0xAC227795
signature.asc
Description: OpenPGP digital signature
_______________________________________________ R-sig-Geo mailing list R-sig-Geo@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-geo