Title: Smoothing parameters for recursive kernel density estimators under double truncation
Authors: Yousri Slaoui - University of Poitiers (France) [presenting]
Abstract: A data-driven bandwidth selection procedure is proposed for the recursive kernel density estimators under double truncation. We show that, using the selected bandwidth and a special stepsize, the proposed recursive estimators will be quite better than the nonrecursive in terms of estimation error and much better in terms of computational costs. We corroborate these theoretical results through a simulation study.