RMdelay is a $(m+1)$-variate stationary covariance model.
which depends on a univariate stationary covariance model $C_0$.
The corresponding covariance function only depends on the difference
$h \in {\bf R}^d$ between two points in $d$-dimensional
space and is given by
$$C(h)=(C_0(h - s_i +s_j))_{i,j=0,\ldots,m}$$
where $s \in {\bf R}^{d\times m}$ and $s_0=0$
Usage
RMdelay(phi,s,var, scale, Aniso, proj)
Arguments
phi
a univariate stationary covariance model, that means an
RMmodel whose vdim equals 1.
s
a $d\times m$-dimensional
shift matrix, where $d$ is the
dimension of the space, giving the components $s=(s_1,\ldots,
s_m)$ where the $s_i$ are vectors.
var,scale,Aniso,proj
optional parameters; same meaning for any
RMmodel. If not passed, the above
covariance function remains unmodified.
RFoptions(seed=0)
x <- y <- seq(-10,10,0.2)
model <- RMdelay(RMstable(alpha=1.9, scale=2), s=c(4,4))
simu <- RFsimulate(model, x, y, grid=TRUE)
plot(simu, zlim="joint")
RFoptions(seed=NA)