mistr: A Computational Framework for Mixture and Composite Distributions

Finite mixtures and composite distributions allow to model the probabilistic representationof data with more generality than simple distributions and are useful to consider in a wide rangeof applications. The R packagemistrprovides an extensible computational framework for creating,transforming, and evaluating these models, together with multiple methods for their visualizationand description. In this paper we present the main computational framework of the package andillustrate its application. In addition, we provide and show functions for data modeling using twospecific composite distributions as well as a numerical example where a composite distribution isestimated to describe the log-returns of selected stocks.