Joint-Conditional Entropy and Mutual Information Estimation Involving Three Random Variables and asymptotic Normality

Authors

  • Amadou Diadie Ba LERSTAD, Gaston Berger University, Saint-Louis, Sénégal.
  • Gane Samb Lo LERSTAD, Gaston Berger University, Saint-Louis, Sénégal and LSTA, Pierre et Marie Curie University, Paris VI, France and AUST-African University of Sciences and Technology, Abuja, Nigeria and Elected Member of the International Statistical Institute (ISI), Netherlands.

DOI:

https://doi.org/10.9734/bpi/tpmcs/v11/8228D

Keywords:

Joint entropy estimation, conditional entropy estimation, mutual information estimation

Abstract

A method of estimating the joint probability mass function of a triplet of discrete random variables is described. This estimator is used to construct the joint-conditional entropies and mutual information estimates involving three random variables. From there almost sure rates of convergence and asymptotic normality are established. The theorical results are validated by simulations.

Published

2021-05-24

How to Cite

Amadou Diadie Ba, & Gane Samb Lo. (2021). Joint-Conditional Entropy and Mutual Information Estimation Involving Three Random Variables and asymptotic Normality. Theory and Practice of Mathematics and Computer Science Vol. 11, 15–38. https://doi.org/10.9734/bpi/tpmcs/v11/8228D

Issue

Theory and Practice of Mathematics and Computer Science Vol. 11

Section

Chapters