A note on the use of binning in kernel smoothing

by Dinh Tuan PHAM.

Abstract: The aim of this paper is to provide a general binning scheme for fast computation of kernel and local polynomial estimation, both in the density and regression context. It is shown that binning is equivalent to using a different equivalent kernel. A method to design binning scheme for which this equivalent kernel approximates a given scaled kernel is proposed.

Key Words: Binning. Fast Computation. Fast Fourier Transform. Discretization. Kernel Estimation. Local Polynomial Regression. Smoothing.

Author:
Dinh Tuan PHAM, Dinh-Tuan.Pham@imag.fr

Editor: Marian Scott , marian@stats.gla.ac.uk

READING THE ARTICLE: You can read the article in portable document (.pdf) format (136397 bytes.)

NOTE: The content of this article is the intellectual property of the authors, who retains all rights to future publication.

This page has been accessed 357 times since April 1, 2007.

Return to the InterStat Home Page.