Structure Determination and Estimation of Hierarchical Archimedean Copulas Based on Kendall Correlation Matrix

Copulas recently emerged in many data analysis and knowledge discovery tasks as a flexible tool for modeling complex multivariate distributions. The paper presents a method for estimating copulas from one of the most popular classes of copulas, namely hierarchical Archimedean copulas. The method is based on the close relationship of the copula structure and the values of Kendall’s tau computed on all its bivariate margins. A simple algorithm implementing the method is provided and its effectiveness is shown in several experiments including its comparison to other available methods.