Publication

A Parzen-Rosenblatt type density estimator for circular data: exact and asymptotic optimal bandwidths

View document

Bibliographic Details
Summary:For the Parzen-Rosenblatt type density estimator for circular data we prove the existence of a minimizer, h_{MISE}(f;K,n), of its exact mean integrated squared error (MISE) and show that it is asymptotically equivalent to the bandwidth h_{AMISE}(f;K,n) that minimizes the leading terms of the MISE, together with the order of convergence of the relative error h_{AMISE}(f;K,n)/h_{MISE}(f;K,n)-1. Some small and moderate sample size comparisons between the two bandwidths are also presented when the underlying density is a mixture of von Mises densities.
Main Authors:Tenreiro, Carlos
Subject:Parzen-Rosenblatt type density estimator circular data exact and asymptotic optimal bandwidths
Year:2024
Country:Portugal
Document type:article
Access type:embargoed access
Associated institution:Universidade de Coimbra
Language:English
Origin:Estudo Geral - Universidade de Coimbra
Description
Summary:For the Parzen-Rosenblatt type density estimator for circular data we prove the existence of a minimizer, h_{MISE}(f;K,n), of its exact mean integrated squared error (MISE) and show that it is asymptotically equivalent to the bandwidth h_{AMISE}(f;K,n) that minimizes the leading terms of the MISE, together with the order of convergence of the relative error h_{AMISE}(f;K,n)/h_{MISE}(f;K,n)-1. Some small and moderate sample size comparisons between the two bandwidths are also presented when the underlying density is a mixture of von Mises densities.