RMwhittlematern {RandomFields}R Documentation

Whittle-Matern Covariance Model

Description

RMmatern is a stationary isotropic covariance model belonging to the Matern family. The corresponding covariance function only depends on the distance r ≥ 0 between two points.

The Whittle model is given by

C(r)=W_{ν}(r)=2^{1- ν} Γ(ν)^{-1}r^{ν}K_{ν}(r)

where ν > 0 and K_ν is the modified Bessel function of second kind.

The Matern model is given by

C(r) = 2^{1- ν} Γ(ν)^{-1} (√{2ν} r)^ν K_ν(√{2ν} r)

Usage

RMwhittle(nu, notinvnu, var, scale, Aniso, proj)

RMmatern(nu, notinvnu, var, scale, Aniso, proj)

Arguments

nu

a numerical value called “smoothness parameter”; should be greater than 0.

notinvnu

logical, if not given the model is defined as above. (default). This argument should not be set by users. See the Notes.

var,scale,Aniso,proj

optional arguments; same meaning for any RMmodel. If not passed, the above covariance function remains unmodified.

Details

RMwhittle and RMmatern are two alternative parametrizations of the same covariance function. The Matern model should be preferred as this model seperates the effects of scaling parameter and the shape parameter.

This is the normal scale mixture model of choice if the smoothness of a random field is to be parametrized: the sample paths of a Gaussian random field with this covariance structure are m times differentiable if and only if ν > m (see Gelfand et al., 2010, p. 24).

Furthermore, the fractal dimension (see also RFfractaldim) D of the Gaussian sample paths is determined by ν: we have

D = d + 1 - ν, 0 < ν < 1

and D = d for ν > 1 where d is the dimension of the random field (see Stein, 1999, p. 32).

If ν=0.5 the Matern model equals RMexp.

For ν tending to a rescaled Gaussian model RMgauss appears as limit of the Matern model.

For generalisations see section ‘seealso’.

Value

The function return an object of class RMmodel

Note

The Matern model called by C(r √(2)) equals the Handcock-Wallis (1994) parametrisation.

The model allows further to be reparameterized by substituting ν for ν^{-1} setting the argument invnu=TRUE. Note that the inversion of ν does not really make sense for the Whittle model. Due to this fact, if the argument invnu is given, the Whittle model changes its definition and becomes identical to the Matern model.

Author(s)

Martin Schlather, schlather@math.uni-mannheim.de

References

Covariance function

Tail correlation function (for 0 < ν ≤ 1/2)

See Also

Examples

RFoptions(seed=0) ## *ANY* simulation will have the random seed 0; set
##                   RFoptions(seed=NA) to make them all random again
x <- seq(0, 1, len=if (interactive()) 100 else 3)
model <- RMwhittle(nu=1, Aniso=matrix(nc=2, c(1.5, 3, -3, 4)))
plot(model, dim=2, xlim=c(-1,1))
z <- RFsimulate(model=model, x, x)
plot(z)


[Package RandomFields version 3.0.62 Index]