bgev2gev: Conversion between blended generalised extreme value...
In evgam: Generalised Additive Extreme Value Models

bgev2gev

R Documentation

Conversion between blended generalised extreme value distribution and generalised extreme value distribution parameters

Description

Conversion between location, scale and shape parameters of the generalised extreme value distribution and corresponding parameters of blended generalised extreme value distribution in both directions.

Usage

bgev2gev(
  location,
  scale,
  shape,
  pa = 0.05,
  pb = 0.2,
  alpha = 0.5,
  beta = 0.5,
  simplify = FALSE
)

gev2bgev(
  location,
  scale,
  shape,
  pa = 0.05,
  pb = 0.2,
  alpha = 0.5,
  beta = 0.5,
  simplify = FALSE
)

Arguments

`location`, `scale`, `shape`	location, scale and shape parameters.
`pa`, `pb`, `alpha`, `beta`	Gumbel to GEV mixing parameters; see Details.
`simplify`	logical; should `simplify2array()` be called at the end?

Details

The blended generalised extreme value distribution has location parameter q_\alpha, scale s_\beta and shape \xi parameters; see, e.g., dbgev. The generalised extreme value distribution's location and scale parameters in its typical form are given by \mu = q_\alpha - s_\beta (\ell_{\alpha, \xi} - 1) / (\ell_{1 - \beta/2, \xi} - \ell_{\beta/2, \xi}) and \sigma = \xi s_\beta / (\ell_{1 - \beta/2, \xi} - \ell_{\beta/2, \xi}). So bgev2gev gives the mapping (q_\alpha, s_\beta, \xi) \mapsto (\mu, \sigma, \xi)). The reverse mapping, (\mu, \sigma, \xi) \mapsto (q_\alpha, s_\beta, \xi)), is given by gev2bgev.

Value

A list or array if simplify = TRUE.

References

Castro-Camilo, D., Huser, R., & Rue, H. (2022). Practical strategies for generalized extreme value-based regression models for extremes. Environmetrics, 33(6), e2742. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1002/env.2742")}