Entropy measure for the quantification of upper quantile interdependence in multivariate distributions

DOI10.1016/J.JMVA.2015.05.004zbMATH Open1323.62054arXiv1408.6681OpenAlexW562334054MaRDI QIDQ495358FDOQ495358

Andras Bárdossy, Jhan Rodríguez

Publication date: 10 September 2015

Published in: Journal of Multivariate Analysis (Search for Journal in Brave)

Abstract: We introduce a new measure of interdependence among the components of a random vector along the main diagonal of the vector copula, i.e. along the line $u_1=ldots=u_J$, for $left(u_1,ldots,u_{J}ight)inleft[0,1ight{]}^J$. Our measure is related to the Shannon entropy of a discrete random variable, hence we call it an "entropy index". This entropy index is invariant with respect to marginal non-decreasing transformations and can be used to quantify the intensity of the vector components association in arbitrary dimensions. We show the applicability of our entropy index by an example with real data of 4 stock prices of the DAX index. In case the random vector is in the domain of attraction of an extreme value distribution, our index is shown to have as limit the distribution's extremal coefficient, which can be interpreted as the effective number of asymptotically independent components in the vector.

Full work available at URL: https://arxiv.org/abs/1408.6681

Recommendations

• Relative Entropy Measures of Multivariate Dependence
• On the entropic measures of stochastic dependence
• On generalized measures of entropy and dependence
• Entropy expressions and their estimators for multivariate distributions
• Entropy inequalities for some multivariate distributions
• A quantile-based generalized dynamic cumulative measure of entropy
• Quantile-based cumulative entropies
• Entropy expressions for multivariate continuous distributions
• Quantile approach of dynamic generalized entropy (divergence) measure

zbMATH Keywords

entropyextremal coefficientmultivariate interdependence

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Measures of association (correlation, canonical correlation, etc.) (62H20) Applications of statistics to actuarial sciences and financial mathematics (62P05) Statistical methods; economic indices and measures (91B82) Statistical methods; risk measures (91G70) Measures of information, entropy (94A17)

Cites Work

• Analysis of Financial Time Series
• Statistics of Extremes
• Extreme value properties of multivariate \(t\) copulas
• A dependence measure for multivariate and spatial extreme values: Properties and inference
• Title not available (Why is that?)
• The herd behavior index: a new measure for the implied degree of co-movement in stock markets
• Measuring stochastic dependence using \(\phi\)-divergence
• Dimensionless Measures of Variability and Dependence for Multivariate Continuous Distributions

Cited In (1)

• Title not available (Why is that?)

Uses Software

• FinTS

This page was built for publication: Entropy measure for the quantification of upper quantile interdependence in multivariate distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q495358)