Clustering Sets of Functional Data by Similarity in Law

We introduce a new clustering method for the classification of functional data sets by their probabilistic law, that is, a procedure that aims to assign data sets to the same cluster if and only if the data were generated with the same underlying distribution. This method has the nice virtue of being non-supervised and non-parametric, allowing for exploratory investigation with few assumptions about the data. Rigorous finite bounds on the classification error are given along with an objective heuristic that consistently selects the best partition in a data-driven manner. Simulated data has been clustered with this procedure to show the performance of the method with different parametric model classes of functional data.