[R-sig-Geo] a krige.conv() question :: covariance parameters

[Paulo Justiniano Ribeiro Jr]

The covariance parameters can be from:
1. a visual fit (which can be permoed with eyefit() in geoR)
2. variofit() for WLS, OLS variogram fit
3. likfit()  for max. likelihood estimates
4. arbitrary values inputed by the user

for the first 3 there will be an object storing the parameters which can 
be passad to krige.control() using the argument obj.model.
In this case it is **not necessary** pass the other parameters 
individually.

an example with basic steps would be

data(s100)
v <- variog(s100, max.dist=1)
vf <- variofit(v)

predLocs <- expand.grid((0:50)/50, (0:50)/50)

kc <- krige.conv(s100, loc=predLocs, krige=krige.control(obj.m=vf))





On Fri, 10 Jun 2011, Lyolya wrote:

> Dear List,
>
> I've been performing the ordinary kriging using the krige.conv() function,
> and I have come across something I don't understand.
> In order perform the kriging, one has to input the covariance parameters in
> krige.control(..., cov.pars=c(a, b), ...). Those can be obtained form the
> variofit() function, right?
>
> variofit() estimates the initial covariance parameters and the estimated
> ones. The least ones are to be input in the krige.control() function, right?
>
> Then, what is to be input in the krige.control(obj.model)? Or this option is
> required in some special cases, and I should rather skip it?
>
> Thank you, in advance.
>
> -- 
> Best
> Lyolya.
>
> 	[[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>


Paulo Justiniano Ribeiro Jr
LEG (Laboratorio de Estatistica e Geoinformacao)
Universidade Federal do Parana
Caixa Postal 19.081
CEP 81.531-990
Curitiba, PR  -  Brasil
Tel: (+55) 41 3361 3573
VOIP: (+55) (41) (3361 3600) 1053 1066
Fax: (+55) 41 3361 3141
e-mail: paulojus AT  ufpr  br
http://www.leg.ufpr.br/~paulojus