Faculty Publications

Title

Multivariate dynamic information

Document Type

Article

Keywords

Entropy, Independence, Kullback-Leibler information, Mutual information, Reliability, Residual life

Journal/Book/Conference Title

Journal of Multivariate Analysis

Volume

98

Issue

2

First Page

328

Last Page

349

Abstract

This paper develops measures of information for multivariate distributions when their supports are truncated progressively. The focus is on the joint, marginal, and conditional entropies, and the mutual information for residual life distributions where the support is truncated at the current ages of the components of a system. The current ages of the components induce a joint dynamic into the residual life information measures. Our study of dynamic information measures includes several important bivariate and multivariate lifetime models. We derive entropy expressions for a few models, including Marshall-Olkin bivariate exponential. However, in general, study of the dynamics of residual information measures requires computational techniques or analytical results. A bivariate gamma example illustrates study of dynamic information via numerical integration. The analytical results facilitate studying other distributions. The results are on monotonicity of the residual entropy of a system and on transformations that preserve the monotonicity and the order of entropies between two systems. The results also include a new entropy characterization of the joint distribution of independent exponential random variables. © 2005 Elsevier Inc. All rights reserved.

Original Publication Date

2-1-2007

DOI of published version

10.1016/j.jmva.2005.08.004

Share

COinS