| profile2d {SpatialExtremes} | R Documentation |
Computes profile surfaces for fitted max-stable models.
## S3 method for class 'maxstab': profile2d(fitted, params, ranges, n = 10, plot = TRUE, ...)
fitted |
An object of class ``maxstab''. Most often, it will be
the output of the function fitmaxstab. |
params |
A character vector giving the two model parameters that are to be profiled. |
ranges |
A matrix corresponding to the ranges for the profiled model parameters that must be explored. Each row corresponds to one model parameter range. |
n |
Integer. The number of profiled model parameter that must be considered. |
plot |
Logical. If TRUE (default), the profile surface is
plotted. |
... |
Extra options that must be passed to the
plot function. |
A list with two arguments: coord and llik. coord
is a matrix representing the grid where the profiled model parameters
are fixed. llik the corresponding pairwise log-likelihood.
This function can be really time consuming!
Mathieu Ribatet
require(RandomFields)
##Define the coordinates of each location
n.site <- 30
locations <- matrix(rnorm(2*n.site, sd = sqrt(.2)), ncol = 2)
colnames(locations) <- c("lon", "lat")
##Simulate a max-stable process - with unit Frechet margins
ms0 <- MaxStableRF(locations[,1], locations[,2], grid=FALSE, model="wh",
param=c(0,1,0,30, .5), maxstable="extr",
n = 30)
ms1 <- t(ms0)
##Now define the spatial model for the GEV parameters
param.loc <- -10 + 2 * locations[,2]
param.scale <- 5 + 2 * locations[,1] + locations[,2]^2
param.shape <- rep(0.2, n.site)
##Transform the unit Frechet margins to GEV
for (i in 1:n.site)
ms1[,i] <- param.scale[i] * (ms1[,i]^param.shape[i] - 1) /
param.shape[i] + param.loc[i]
##Define a model for the GEV margins to be fitted
##shape ~ 1 stands for the GEV shape parameter is constant
##over the region
loc.form <- loc ~ lat
scale.form <- scale ~ lon + (lat^2)
shape.form <- shape ~ 1
##Fit a max-stable process
## 1- using the Schlather representation
## Not run:
fitted <- fitmaxstab(ms1, locations, "schlather", loc.form, scale.form,
shape.form)
## End(Not run)
##Plot the profile pairwise log-likelihood for the smooth parameter
## Not run:
ranges <- rbind(c(9,11), c(.3, .8))
profile2d(fitted, c("range", "smooth"), ranges = ranges)
## End(Not run)