A fast epigraph and hypograph-based approach for clustering functional data

Abstract Clustering techniques for multivariate data are useful tools in Statistics that have been fully studied the literature. However, there is limited literature on clustering methodologies functional data. Our proposal consists of a procedure using The idea to reduce problem into one by applying epigraph and hypograph indexes original curves their first and/or second derivatives. All information given therefore transformed context, being informative enough usual be efficient. performance this new methodology evaluated through simulation study also illustrated real sets. results compared some other procedures