A1035
Title: Cluster analysis of directional data based on data depths
Authors: Giuseppe Pandolfo - University of Naples Federico II (Italy) [presenting]
Antonio D Ambrosio - University of Naples Federico II (Italy)
Abstract: A new depth-based clustering procedure for directional data is proposed. Such a method is fully non-parametric and has the advantage of being flexible and applicable even in high dimensions when a suitable notion of depth is adopted. The introduced technique is evaluated through an extensive simulation study. In addition, a real data example in text mining is given to explain its effectiveness in comparison with other existing directional clustering algorithms.
