In the article An entropy-based measure of dependencebetween two groups of random variables, the K-dependence coefficient ordependence coefficient is defined with entropy and conditional entropy tomeasure the degree of dependence of one group of categorical randomvariables on another group of categorical random variables. Also, theconcept of the K-dependence coefficient is extended by defining the partialK-dependence coefficient and the semi-partial K-dependence coefficientwith which the K-dependence coefficient decomposition expression isestablished mathematically. The K-Dependence coefficient decompositionexpression shows that K-dependence coefficient is of additive structure andtherefore, according to Measure Theory, K-dependence coefficient is ameasure of the degree of dependence of one group of categorical randomvariables on another group of categorical random variables.In this commentary, first we introduce the Entropy and Information graphicalrepresentation to help us understand K-dependence coefficient. Next, weintroduce the concept of measure followed by a briefly discussion on K-dependence coefficient additive structure together with several othermeasures, such as coefficient of determination, Entropy and Probability.Finally, we introduce some ideas to extend K-dependence coefficient.

Article An entropy-based measure of dependence between two groups of...

Preprint Commentary on An entropy-based measure of dependence between...