GEV {qrmtools}

Generalized Extreme Value Distribution

Description

Density, distribution function, quantile function and random variate generation for the generalized extreme value distribution (GEV).

Usage

dGEV(x, shape, loc = 0, scale = 1, log = FALSE)
pGEV(q, shape, loc = 0, scale = 1, lower.tail = TRUE, log.p = FALSE)
qGEV(p, shape, loc = 0, scale = 1, lower.tail = TRUE, log.p = FALSE)
rGEV(n, shape, loc = 0, scale = 1)

Arguments

x, q

vector of quantiles.

p

vector of probabilities.

n

number of observations.

shape

GEV shape parameter \xi, a real.

loc

GEV location parameter \mu, a real.

scale

GEV scale parameter \sigma, a positive real.

lower.tail

logical; if TRUE (default) probabilities are P(X \le x) otherwise, P(X > x).

log, log.p

logical; if TRUE, probabilities p are given as log(p).

Details

The distribution function of the generalized extreme value distribution is given by

F(x) = \left\{ \begin{array}{ll} \exp(-(1-\xi(x-\mu)/\sigma)^{-1/\xi}), & \xi\neq 0,\ 1+\xi(x-\mu)/\sigma>0,\\ \exp(-e^{-(x-\mu)/\sigma}), & \xi = 0, \end{array}\right.

where \sigma>0.

Value

dGEV() computes the density, pGEV() the distribution function, qGEV() the quantile function and rGEV() random variates of the generalized extreme value distribution.

Author(s)

Marius Hofert

References

McNeil, A. J., Frey, R., and Embrechts, P. (2015). Quantitative Risk Management: Concepts, Techniques, Tools. Princeton University Press.

Examples

## Basic sanity checks
plot(pGEV(rGEV(1000, shape = 0.5), shape = 0.5)) # should be U[0,1]
curve(dGEV(x, shape = 0.5), from = -3, to = 5)