\name{RMSadvanced}
\alias{RMSadvanced}
\title{Scaling operator -- comments for advanced applications}
\description{
Here advances uses are given for the arguments
\code{var}, \code{scale}, \code{Aniso}, \code{proj} that are available
to most of the models
}
\section{Usage}{
RMS(phi, var, scale, Aniso, proj, anisoT)
}
\section{Arguments}{
\describe{
\item{phi}{submodel}
\item{var}{Instead of a constant it can be
also an arbitrary non-negative function, see \code{\link{R.}}
and \command{\link{RMuser}} for defining arbitrary functions.
}
\item{scale}{instead of a positive constant it can be an arbitrary,
positive
deterministic function. In case of the latter, the scale should be
given by one of the functions \command{\link{RMbubble}} or
\command{\link{RMscale}}. In case none of them are given,
\command{\link{RMscale}} is assumed with scale penality
\eqn{\|s(x) - s(y)\|^2} for the square of the norm.
The scale can be also a random variable
in case of Bayesian modelling.
}
\item{Aniso}{matrix or \code{\link{RMmodel}}.
Instead of a matrix, \code{Aniso} can be an arbitrary, vector-valued
function .
}
\item{proj}{is the optional projection vector which defines a diagonal
matrix of zeros and ones and \code{proj} gives the
positions of the ones (integer values between 1 and the dimension of
\eqn{x}). It also allows for the values \code{'space'} and
\code{'time'} in case of space-time modelling.
}
\item{anisoT}{the transpose of the anisotropy matrix \eqn{B},
multiplied from the left by a distance vector \eqn{x}, i.e. \eqn{x^\top B}.
}
}
}
\section{Details}{
See the reference for Gneitings nsst model used for modelling scales.
See also the example below.
}
\section{Value}{
\command{\link{RMSadvanced}} returns an object of class \code{\link[=RMmodel-class]{RMmodel}}.
}
\references{
\itemize{
\item Bonat, W.H. , Ribeiro, P. Jr. and Schlather, M. (2019)
Modelling non-stationarity in scale. In preparation.
}
}
\me
\seealso{
\command{\link{RMS}},
\command{\link{RMblend}} for a different approach on modelling
different scales
}
\examples{\dontshow{StartExample(FALSE)}
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, if (interactive()) 0.01 else 0.5)
d <- sqrt(rowSums(as.matrix(expand.grid(x-0.5, x-0.5))^2))
d <- matrix(d < 0.25, nc=length(x))
image(d)
scale <- RMcovariate(data=as.double(d) * 2 + 0.5, raw=TRUE)
S <- RMexp(scale = scale)
plot(zS <- RFsimulate(S, x, x))
CS <- RFcovmatrix(S, x, x)
\dontshow{FinalizeExample()}}
\keyword{spatial}
\keyword{models}