map.latent {SpatialExtremes}

Two dimensional map from a Bayesian hierarchical model

Description

This function plots 2D maps from a Markov chain.

Usage

map.latent(fitted, x, y, covariates = NULL, param = "quant", ret.per =
100, col = terrain.colors(64), plot.contour = TRUE, fun = mean, level =
0.95, show.data = TRUE, control = list(nlines = 500), ...)

Arguments

fitted

An object of class "latent". Typically this will be the output of latent.

x, y

Numeric vector specifying the coordinates of the grid points.

covariates

An array specifying the covariates at each grid point defined by x and y. If NULL, no covariate is needed.

param

A character string. Must be one of "loc", "scale", "shape" or "quant" for a map of the location, scale, shape parameters or for a map of a specified quantile.

ret.per

A numeric giving the return period for which the quantile map is plotted. It is only required if param = "quant".

col

A list of colors such as that generated by 'rainbow', 'heat.colors', 'topo.colors', 'terrain.colors' or similar functions.

plot.contour

Logical. If TRUE (default), contour lines are added to the plot.

fun

A character string specifying the function to be used to get posterior point estimates. The default is to take posterior means.

level

A numeric specifying the significance level for the pointwise credible intervals.

show.data

Logical. Should the locations where have observed the process have to be plotted?

control

A list with named components specifying options to be passed to rgp. Typically one might want specify nlines to reduce the computational demand.

...

Several arguments to be passed to the image function.

Value

A plot and a invisible list containing all the data required to do the plot.

Author(s)

Mathieu Ribatet

See Also

condrgp, map

Examples

## Not run: 
## Generate realizations from the model
n.site <- 30
n.obs <- 50
coord <- cbind(lon = runif(n.site, -10, 10), lat = runif(n.site, -10 , 10))

gp.loc <- rgp(1, coord, "powexp", sill = 4, range = 20, smooth = 1)
gp.scale <- rgp(1, coord, "powexp", sill = 0.4, range = 5, smooth = 1)
gp.shape <- rgp(1, coord, "powexp", sill = 0.01, range = 10, smooth = 1)

locs <- 26 + 0.5 * coord[,"lon"] + gp.loc
scales <- 10 + 0.2 * coord[,"lat"] + gp.scale
shapes <- 0.15 + gp.shape

data <- matrix(NA, n.obs, n.site)
for (i in 1:n.site)
  data[,i] <- rgev(n.obs, locs[i], scales[i], shapes[i])

loc.form <- y ~ lon
scale.form <- y ~ lat
shape.form <- y ~ 1

hyper <- list()
hyper$sills <- list(loc = c(1,8), scale = c(1,1), shape = c(1,0.02))
hyper$ranges <- list(loc = c(2,20), scale = c(1,5), shape = c(1, 10))
hyper$smooths <- list(loc = c(1,1/3), scale = c(1,1/3), shape = c(1, 1/3))
hyper$betaMeans <- list(loc = rep(0, 2), scale = c(9, 0), shape = 0)
hyper$betaIcov <- list(loc = solve(diag(c(400, 100))),
                       scale = solve(diag(c(400, 100))),
                       shape = solve(diag(c(10), 1, 1)))

## We will use an exponential covariance function so the jump sizes for
## the shape parameter of the covariance function are null.
prop <- list(gev = c(2.5, 1.5, 0.2), ranges = c(0.7, 0.75, 0.9), smooths = c(0,0,0))
start <- list(sills = c(4, .36, 0.009), ranges = c(24, 17, 16), smooths
              = c(1, 1, 1),  beta = list(loc = c(26, 0.5), scale = c(10, 0.2),
                               shape = c(0.15)))

## Generate a Markov chain
mc <- latent(data, coord, loc.form = loc.form, scale.form = scale.form,
             shape.form = shape.form, hyper = hyper, prop = prop, start = start,
             n = 100)

x.grid <- y.grid <- seq(-10, 10, length = 50)
map.latent(mc, x.grid, y.grid, param = "shape")

## End(Not run)