An improved data-based algorithm for choosing the window width when estimating the density at a point

Sheather [3] proposed a data-based algorithm for choosing the window width when estimating the density at a point by a kernel estimator. Unfortunately, for some densities the windows widths produced by the algorithm have considerable bias. More importantly the resulting density estimator is not scal...

Full description

Saved in:

Bibliographic Details
Published in	Computational statistics & data analysis Vol. 4; no. 1; pp. 61 - 65
Main Author	Sheather, Simon J.
Format	Journal Article
Language	English
Published	Elsevier B.V 01.06.1986 Elsevier
Series	Computational Statistics & Data Analysis
Subjects	Kernel density estimation Smoothing parameter Kernel density estimation Smoothing parameter
Online Access	Get full text
ISSN	0167-9473 1872-7352
DOI	10.1016/0167-9473(86)90026-5

Cover

More Information
Summary:	Sheather [3] proposed a data-based algorithm for choosing the window width when estimating the density at a point by a kernel estimator. Unfortunately, for some densities the windows widths produced by the algorithm have considerable bias. More importantly the resulting density estimator is not scale invariant. In this note we show how a modification to the algorithm overcomes these two problems.
ISSN:	0167-9473 1872-7352
DOI:	10.1016/0167-9473(86)90026-5