I'm performing ordinary and simple kriging from a set of non-negative
values:
>krige.control.sk<-krige.control(type.krige="sk",obj.model=my.variogram.model,beta=my.variogram.model$beta)
>sk<-krige.conv(cadiz.geo,data=amostragem.cadiz$dia1.std,locations=as.matrix(cadiz.polygrid[,c(1,2)]),krige=krige.control.sk)
krige.conv: model with constant mean
krige.conv: Kriging performed using global neighbourhood
and
>krige.control.ok<-krige.control(type.krige="ok",obj.model=my.variogram.model)
>ok<-krige.conv(cadiz.geo,data=amostragem.cadiz$dia1.std,locations=as.matrix(cadiz.polygrid[,c(1,2)]),krige=krige.control.ok)
krige.conv: model with constant mean
krige.conv: Kriging performed using global neighbourhood
where my.variogram.model is gaussian fitted through variofit with
"cressie" weigths.
I'm getting the same predicted values for both models, 12% of them
being negative. Is it because simple and ordinary kriging predictions
are not including the overall mean? If this is the case what mean should
I use?
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at
stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
