A0317
Title: Non-parametric dimensionality detection for functional data
Authors: Enea Bongiorno - Universita del Piemonte Orientale (Italy) [presenting]
Kwo Lik Lax Chan - Universita del Piemonte Orientale (Italy)
Aldo Goia - University of Eastern Piedmont Amedeo Avogadro (Italy)
Abstract: Several methodologies in functional statistics are based on multistep strategies, which, as a first step, involve a dimensionality reduction technique. Usually, a critical aspect of the latter technique is the choice of the number of components to use. We present a non-parametric strategy for this choice based on the notion of complexity for a process. This concept can be interpreted as a sort of degree of freedom of the process and is defined starting from an appropriate factorization for the Small Ball probability of the process itself. The methodology will be illustrated through simulations and applications.
