Pseudo-quantile functional data clustering (Q2181734)

This paper studies the problem of functional data clustering. Functional data are inherently infinite-dimensional, so classical clustering technique are not appropriate for them. A new approach for functional data clustering based on the concept of an asymetric norm is considered. Pseudo-quantiles, such as M-quantiles and expectiles, are used to discover distributional information about hidden structure in the data at various levels. Numerical examples are given for justification of the given methods.