https://github.com/cran/RandomFields
Tip revision: 51663e75fb9ba1d6cf08d8f47db96cebfe1bb458 authored by Martin Schlather on 04 December 2013, 00:00:00 UTC
version 3.0.5
version 3.0.5
Tip revision: 51663e7
RMexp.Rd
\name{RMexp}
\alias{RMexp}
\title{Exponential Covariance Model}
\description{
\command{\link{RMexp}} is a stationary isotropic covariance model whose
corresponding covariance function only depends
on the distance \eqn{r \ge 0}{r \ge 0} between
two points and is given by
\deqn{C(r) = e^(-r).}{C(r) = exp(-r).}
}
\usage{
RMexp(var, scale, Aniso, proj)
}
\arguments{
\item{var,scale,Aniso,proj}{optional parameters; same meaning for any
\command{\link{RMmodel}}. If not passed, the above
covariance function remains unmodified.}
}
\details{
This model is a special case of the Whittle covariance model (see \command{\link{RMwhittle}}) if \eqn{\nu=\frac{1}{2}}{\nu=0.5} and of the symmetric stable family (see \command{\link{RMstable}}) if \eqn{\nu = 1}{\nu=1}. Moreover,
it is the continuous-time analog of the first order autoregressive time
series covariance structure.
The exponential covariance function is a normal scale mixture.
}
\value{
\command{\link{RMexp}} returns an object of class \code{\link[=RMmodel-class]{RMmodel}}.
}
\references{ Gelfand, A. E., Diggle, P., Fuentes, M. and Guttorp,
P. (eds.) (2010) \emph{Handbook of Spatial Statistics.}
Boca Raton: Chapman & Hall/CRL.
}
\author{Martin Schlather, \email{schlather@math.uni-mannheim.de} \url{http://ms.math.uni-mannheim.de}
}
\seealso{
\command{\link{RMwhittle}},
\command{\link{RMstable}},
\command{\link{RMmodel}},
\command{\link{RFsimulate}},
\command{\link{RFfit}}.
}
\keyword{spatial}
\keyword{models}
\examples{
set.seed(0)
model <- RMexp()
x <- seq(0, 10, if (interactive()) 0.02 else 1)
plot(model, ylim=c(0,1))
plot(RFsimulate(model, x=x))
}