hkCopula: Constructor of a hierarchical Kendall copula

In BenGraeler/spcopula: Copula Driven Analysis - Multivariate, Spatial, Spatio-Temporal

Description

A copula object from the copula family of hierarchical Kendall copulas. Cluster copulas are linked via their Kendall distribution functions in a nesting copula.

Usage

hkCopula(nestingCop, clusterCops, kenFuns=NULL)

Arguments

nestingCop	The nesting copula that combines the clusters. Any copula is allowed.
clusterCops	A list of lists defining the cluster copulas and the indices used. Any copula is allowed, but the evaluation of the Kendall distribution function is time consuming for many families. Archimedean copulas are preferred from a computation time point of view.
kenFuns	A list of corresponding Kendall distribution functions of the same length as clusterCops.

Value

A hkCopula object that behaves (almost) like any other copula from the copula package.

Author(s)

Benedikt Graeler

References

Brechmann, Eike Christian. "Hierarchical Kendall copulas: Properties and inference." Canadian Journal of Statistics 42.1 (2014): 78-108.

See Also

See also hkCopula, vineCopula.

Examples

hkCop <- hkCopula(gumbelCopula(5),list(list(frankCopula(3), c(1,2)),
                                       list(claytonCopula(3), c(3,4))))
hkCop

dCopula(matrix(runif(400), 100), hkCop)

BenGraeler/spcopula documentation built on Nov. 20, 2020, 4:07 p.m.