[R-sig-Geo] is the nugget parameter included in the "VariogramLine" function in gstat?

[Edzer Pebesma]

On 12/04/2017 05:30 PM, bernard julien wrote:
> Good day all,
> 
> 
> I would like to know apply a smoothing effect to my kriging and thus, would like to include the nugget when generating my Covariance matrices for both measured and unmeasured locations.
> 
> 
> I am generating my Covariance matrices using the variogramLine function as follows:
> 
> 
> covariates <= variogram( response~covariate1+covariate2, spatial_df,cressie=TRUE)
> 
> A <- vgm("Exp")
> myvariog<- fit.variogram(covariates, A)
> 
> V = variogramLine( myvariog, dist_vector = sp::spDists(as.matrix(measured), as.matrix(measured), longlat=FALSE),covariance = TRUE)
> 
> Is it assumed the nugget is included when forming the Covariance matrix when using VariogramLine?

Yes: it will add to the entries corresponding to zero values in dist_vector.

> variogramLine(vgm(1, "Exp", 1, 0), dist_vector =
matrix(c(0,1,1,0),2),covariance=TRUE)
          [,1]      [,2]
[1,] 1.0000000 0.3678794
[2,] 0.3678794 1.0000000
> variogramLine(vgm(1, "Exp", 1, 1), dist_vector =
matrix(c(0,1,1,0),2),covariance=TRUE)
          [,1]      [,2]
[1,] 2.0000000 0.3678794
[2,] 0.3678794 2.0000000


> 
> 
> thank you.
> 
> Bernard
> 
> 	[[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
> 

-- 
Edzer Pebesma
Institute for Geoinformatics
Heisenbergstrasse 2, 48151 Muenster, Germany
Phone: +49 251 8333081