A Reweighting Approach to Robust Clustering

Abstract

An iteratively reweighted approach for robust clustering is presented in this work. The method is initialized with a very robust clustering partition based on an high trimming level. The initial partition is then refined to reduce the number of wrongly discarded observations and substantially increase efficiency. Simulation studies and real data examples indicate that the final clustering solution is both robust and efficient, and naturally adapts to the true underlying contamination level.