exdex (version 1.0.1)

vcov.spm: Calculate Variance-Covariance Matrix for an "spm" object

Description

vcov method for class c("spm", "exdex").

Usage

# S3 method for spm
vcov(object, maxima = c("sliding", "disjoint"),
  estimator = "all", ...)

Arguments

object

and object of class c("spm", "exdex") returned from spm.

maxima

A character scalar specifying whether to return the estimated variance of the estimator of the extremal index \(\theta\) based on sliding maxima or on disjoint maxima.

estimator

A character vector specifying which of the three variants of the semiparametric maxima estimator to use: "N2015", "BB2018" or "BB2018b". See spm for details. If estimator = "all" then the estimated variances of all variants are returned.

...

Further arguments. None are used.

Value

A 1 by 1 numeric matrix if estimator = "N2015" or "BB2018" and a vector of length 2 if estimator = "both", containing the estimated variance(s) of the estimator(s).

References

Northrop, P. J. (2015) An efficient semiparametric maxima estimator of the extremal index. Extremes 18(4), 585-603. https://doi.org/10.1007/s10687-015-0221-5

Berghaus, B., Bucher, A. (2018) Weak convergence of a pseudo maximum likelihood estimator for the extremal index. Ann. Statist. 46(5), 2307-2335. https://doi.org/10.1214/17-AOS1621