The aim of this chapter is to present and describe the R package CoClust, which enables implementing a clustering algorithm based on the copula function. The copula-based clustering algorithm, called CoClust, was introduced by Di Lascio and Giannerini in 2012 (Journal of Classification, 29(1):50–75), improved in 2016 (Statistical Papers, p.1–17, DOI 10.1007/s00362-016-0822-3), and is able to find clusters according to the complex multivariate dependence structure of the data-generating process. Hence, among other advantages, the CoClust overcomes the limitations of classic approaches that only deal with linear bivariate relationships. The first part of the chapter briefly describes the clustering algorithm. The second part illustrates the clustering procedure through the R package CoClust and presents numerical examples showing how the main R commands can be used to perform a fully developed clustering of multivariate dependent data.
Part of the book: Recent Applications in Data Clustering