Translator Disclaimer
March, 1987 On the Amount of Noise Inherent in Bandwidth Selection for a Kernel Density Estimator
Peter Hall, J. S. Marron
Ann. Statist. 15(1): 163-181 (March, 1987). DOI: 10.1214/aos/1176350259

Abstract

In the setting of kernel density estimation, data-driven bandwidth, i.e., smoothing parameter, selectors are considered. It is seen that there is a well-defined, and surprisingly restrictive, bound on the rate of convergence of any automatic bandwidth selection method to the optimum. The method of least squares cross-validation achieves this bound.

Citation

Download Citation

Peter Hall. J. S. Marron. "On the Amount of Noise Inherent in Bandwidth Selection for a Kernel Density Estimator." Ann. Statist. 15 (1) 163 - 181, March, 1987. https://doi.org/10.1214/aos/1176350259

Information

Published: March, 1987
First available in Project Euclid: 12 April 2007

zbMATH: 0667.62022
MathSciNet: MR885730
Digital Object Identifier: 10.1214/aos/1176350259

Subjects:
Primary: 62G05
Secondary: 62E20, 62H99

Rights: Copyright © 1987 Institute of Mathematical Statistics

JOURNAL ARTICLE
19 PAGES


SHARE
Vol.15 • No. 1 • March, 1987
Back to Top