extRemes (version 2.2)

findpars: Get EVD Parameters

Description

Obtain the parameters from an fevd object. This function differs greatly from distill.

Usage

findpars(x, ...)
# S3 method for fevd
findpars(x, ...)
# S3 method for fevd.bayesian
findpars(x, burn.in = 499, FUN = "mean",
    use.blocks = FALSE, ..., qcov = NULL)
# S3 method for fevd.lmoments
findpars(x, ...)
# S3 method for fevd.mle
findpars(x, use.blocks = FALSE, ..., qcov = NULL)

Value

A list object is returned with components

location, scale, shape

vector of parameter values (or NULL if the parameter is not in the model). For stationary models, or for parameters that are fixed in the otherwise non-stationary model, the vectors will repeat the parameter value. The length of the vectors equals the length of the data used to fit the models.

Arguments

x

A list object of class “fevd” as returned by fevd.

burn.in

number giving the burn in value. The first 1:burn.in will not be used in obtaining parmaeter estiamtes.

FUN

character string naming a function, or a function, to use to find the parameter estimates from the MCMC sample. Default is to take the posterior mean (after burn in).

use.blocks

logical: If TRUE and x was fit with blocks provided, returns parameters for each block

...

Not used.

qcov

numeric matrix with rows the same length as q and columns equal to the number of parameters (+ 1 for the threshold, if a POT model). This gives any covariate values for a nonstationary model. If NULL, and model is non-stationary, only the intercept terms for modeled parameters are used, and if a non-constant threshold, only the first threshold value is used. Not used if model is stationary.

Author

Eric Gilleland

Details

This function finds the EVD parameters for each value of the covariates in a non-stationary model. In the case of a stationary model, it will return vectors of length equal to the length of the data that simply repeat the parameter(s) value(s).

Note that this differs greatly from distill, which simply returns a vector of the length of the number of parameters in the model. This function returns a named list containing the EVD parameter values possibly for each value of the covariates used to fit the model. For example, if a GEV(location(t), scale, shape) is fit with location(t) = mu0 + mu1 * t, say, then the “location” component of the returned list will have a vector of mu0 + mu1 * t for each value of t used in the model fit.

See Also

fevd, distillery::distill, parcov.fevd

Examples

z <- revd(100, loc=20, scale=0.5, shape=-0.2)
fit <- fevd(z)
fit

findpars(fit)

if (FALSE) {
data(PORTw)
fit <- fevd(TMX1, PORTw, location.fun=~AOindex, units="deg C")
fit

findpars(fit)

}