[R-sig-Geo] KED trend coefficients in Gstat with R

[Edzer Pebesma]

On 10/26/2010 09:02 AM, eric.jabot at ujf-grenoble.fr wrote:
> Hello,
> 
> I would like to know if there is a way to get the trend coefficents when
> doing kriging with external drift. I would like to compare with the
> coefficients that I can have when doing temperature = f(altitude) for a
> sample of stations.
> Thanks for your answer(s).
> 
> Eric
> 
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo

Eric, try

library(gstat)
demo(blue)

shows you one way how to do this. It is a bit tricky, because you're
using prediction equations (that disregard the residual, if BLUE=TRUE)
to get them. But then, in the end if your regression model is

  beta0 * Intercept + beta1 * altitude,

setting Intercept to 0 and altitude to 1 gives you beta1, with its
estimation error.

Another, maybe more direct way could be find by using the mixed models
in package nlme.
-- 
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.52north.org/geostatistics      e.pebesma at wwu.de