tsicEmp {satdad}R Documentation

Empirical tail superset importance coefficients.

Description

Computes on a sample the tail superset importance coefficients (tsic) associated with threshold k. The value may be renormalized by the empirical global variance (Sobol version) and/or by its theoretical upper bound.

Usage

tsicEmp(sample, ind = 2, k, sobol = FALSE, norm = FALSE)

Arguments

sample

A (n times d) matrix.

ind

A character string among "with.singletons" and "all" (without singletons), or an integer in \{2,...,d\} or a list of subsets from \{1,...,d\}. The default is ind = 2, all pairwise coefficients are computed.

k

An integer smaller or equal to n.

sobol

A boolean. 'FALSE' (the default). If 'TRUE': the index is normalized by the empirical global variance.

norm

A boolean. 'FALSE' (the default). If 'TRUE': the index is normalized by its theoretical upper bound.

Details

The theoretical functional decomposition of the variance of the stdf \ell consists in writing D(\ell) = \sum_{I \subseteq \{1,...,d\}} D_I(\ell) where D_I(\ell) measures the variance of \ell_I(U_I) the term associated with subset I in the Hoeffding-Sobol decomposition of \ell ; note that U_I represents a random vector with independent standard uniform entries.

Fixing a subset of components I, the theoretical tail superset importance coefficient is defined by \Upsilon_I(\ell)=\sum_{J \supseteq I} D_J(\ell). A theoretical upper bound for tsic \Upsilon_I(\ell) is given by Theorem 2 in Mercadier and Ressel (2021) which states that \Upsilon_I(\ell)\leq 2(|I|!)^2/((2|I|+2)!).

Here, the function tsicEmp evaluates, on a n-sample and threshold k, the empirical tail superset importance coefficient \hat{\Upsilon}_{I,k,n} the empirical counterpart of \Upsilon_I(\ell).

Under the option sobol = TRUE, the function tsicEmp returns \dfrac{\hat{\Upsilon}_{I,k,n}}{\hat{D}_{k,n}} the empirical counterpart of \dfrac{\Upsilon_I(\ell)}{D_I(\ell)}.

Under the option norm = TRUE, the quantities are multiplied by \dfrac{(2|I|+2)!}{2(|I|!)^2}.

Proposition 1 and Theorem 2 of Mercadier and Roustant (2019) provide several rank-based expressions

\hat{\Upsilon}_{I,k,n}=\frac{1}{k^2}\sum_{s=1}^n\sum_{s^\prime=1}^n \prod_{t\in I}(\min(\overline{R}^{(t)}_s,\overline{R}^{(t)}_{s^\prime})-\overline{R}^{(t)}_{s}\overline{R}^{(t)}_{s^\prime}) \prod_{t\notin I} \min(\overline{R}^{(t)}_s,\overline{R}^{(t)}_{s^\prime})

\hat{D}_{k,n}=\frac{1}{k^2}\sum_{s=1}^n\sum_{s^\prime=1}^n \prod_{t\in I}\min(\overline{R}^{(t)}_s,\overline{R}^{(t)}_{s^\prime})- \prod_{t\in I}\overline{R}^{(t)}_{s}\overline{R}^{(t)}_{s^\prime}

where

Value

The function returns a list of two elements:

Author(s)

Cécile Mercadier (mercadier@math.univ-lyon1.fr)

References

Mercadier, C. and Ressel, P. (2021) Hoeffding–Sobol decomposition of homogeneous co-survival functions: from Choquet representation to extreme value theory application. Dependence Modeling, 9(1), 179–198.

Mercadier, C. and Roustant, O. (2019) The tail dependograph. Extremes, 22, 343–372.

See Also

graphsEmp, ellEmp

Examples


## Fix a 6-dimensional asymmetric tail dependence structure
ds <- gen.ds(d = 6, sub = list(1:4,5:6))

## Plot the  tail dependograph
graphs(ds)

## Generate a 1000-sample of Archimax Mevlog random vectors
## associated with ds and underlying distribution exp
sample <- rArchimaxMevlog(n = 1000, ds = ds, dist = "exp", dist.param = 1.3)

## Compute tsic values associated with subsets
## of cardinality 2 or more \code{ind = "all"}
res <- tsicEmp(sample = sample, ind = "all", k = 100, sobol = TRUE, norm = TRUE)

## Select the significative tsic
indices_nonzero <- which(res$tsic %in% boxplot.stats(res$tsic)$out == TRUE)

## Subsets associated with significative tsic reflecting the tail support
as.character(res$subsets[indices_nonzero])

## Pairwise tsic are obtained by
res_pairs <- tsicEmp(sample = sample, ind = 2, k = 100, sobol = TRUE, norm = TRUE)

## and plotted in the tail dependograph
graphsEmp(sample, k = 100)

[Package satdad version 1.1 Index]