gev2frech {SpatialExtremes}R Documentation

Transforms GEV data to unit Frechet ones and vice versa

Description

Transforms GEV data to unit Frechet ones and vice versa

Usage

gev2frech(x, loc, scale, shape, emp = FALSE)
frech2gev(x, loc, scale, shape)

Arguments

x The data to be transformed to unit Frechet or ordinary GEV margins
loc, scale, shape The location, scale and shape parameters of the GEV.
emp Logical. If TRUE, data are transformed to unit Frechet margins using the empirical CDF.

Details

If Y is a random variable with a GEV distribution with location μ, scale σ and shape xi. Then,

Z = [1 + xi (Y - μ) / σ]_+^(1/xi)

is unit Frechet distributed - where x_+ = max(0, x).

If Z is a unit Frechet random variable. Then,

Y = μ + σ (Z_+^(xi) - 1) / xi

is unit GEV distributed with location, scale and shape parameters equal to μ, σ and xi respectively.

Value

Returns a numeric vector with the same length of x

Author(s)

Mathieu Ribatet

Examples

x <- c(2.2975896, 1.6448808, 1.3323833, -0.4464904, 2.2737603,
    -0.2581876, 9.5184398, -0.5899699, 0.4974283, -0.8152157)
y <- gev2frech(x, 1, 2, .2)
y
frech2gev(y, 1, 2, .2)

[Package SpatialExtremes version 1.1-1 Index]