A0331
Title: A geometry-based highest density region estimator for manifold data
Authors: Diego Bolon - Universite Libre de Bruxelles (Belgium) [presenting]
Rosa Crujeiras - University of Santiago de Compostela (Spain)
Alberto Rodriguez-Casal - University of Santiago de Compostela (Spain)
Abstract: Highest-density regions (HDRs) are the subsets of the support where the density function of the data exceeds a given (and usually high) threshold. Estimating the HDRs of a population from a data sample has multiple practical applications, like data clustering or the comparison of two (or more) populations. A new geometry-based HDR estimator is introduced for manifold data. The new approach combines an underlying density estimator with some prior geometric information on the true HDRs of the underlying population. The consistency and the convergence rate of the new estimator are derived. Finally, the performance in practice of the new HDR estimator is illustrated with a real data example.
