simulPareto: Simulate log-Gaussian Pareto random vectors

In r-fndv/mvPot: Multivariate Peaks-over-Threshold Modelling for Spatial Extreme Events

Simulate log-Gaussian Pareto random vectors

Description

simulPareto provides n replicates of the multivariate Pareto distribution associated to log-Gaussian random function with semi-variogram vario.

Usage

simulPareto(n, loc, vario, nCores = 1, cl = NULL)

Arguments

n	Number of replicates desired.
loc	Matrix of coordinates as given by expand.grid().
vario	Semi-variogram function.
nCores	Number of cores used for the computation
cl	Cluster instance as created by makeCluster of the parallel package. Make sure the random number generator has been properly initialized with clusterSetRNGStream().

Details

The algorithm used here is based on the spectral representation of the Brown–Resnick model as described in Dombry et al. (2015). It provides n replicates conditioned that mean(x) > 1 on the unit Frechet scale.

Value

List of n random vectors drawn from a multivariate Pareto distribution with semi-variogram vario.

References

Dombry, C., Engelke, S. and M. Oesting. Exact simulation of max-stable processes. Biometrika, 103(2), 303-317.

Examples

#Define variogram function
vario <- function(h){
   1 / 2 * norm(h,type = "2")^1.5
}

#Define locations
loc <- expand.grid(1:4, 1:4)

#Simulate data
obs <- simulPareto(100, loc, vario)

r-fndv/mvPot documentation built on July 5, 2025, 1:35 a.m.