White Rose University Consortium logo
University of Leeds logo University of Sheffield logo York University logo

On boosting kernel regression

Di Marzio, M and Taylor, CC (2008) On boosting kernel regression. Journal of Statistical Planning and Inference, 138 (8). 2483 - 2498 . ISSN 0378-3758


Download (570Kb)


In this paper we propose a simple multistep regression smoother which is constructed in an iterative manner, by learning the Nadaraya-Watson estimator with L-2 boosting. We find, in both theoretical analysis and simulation experiments, that the bias converges exponentially fast. and the variance diverges exponentially slow. The first boosting step is analysed in more detail, giving asymptotic expressions as functions of the smoothing parameter, and relationships with previous work are explored. Practical performance is illustrated by both simulated and real data.

Item Type: Article
Copyright, Publisher and Additional Information: © 2008 Elsevier B.V. This is an author produced version of a paper subsequently published in Journal of Statistical Planning and Inference. Uploaded in accordance with the publisher's self-archiving policy.
Keywords: bias reduction, Boston housing data, convolution, cross-validation, local polynomial fitting, positive definite kernels, twicing, consistency, classification
Institution: The University of Leeds
Academic Units: The University of Leeds > Faculty of Maths and Physical Sciences (Leeds) > School of Mathematics (Leeds) > Statistics (Leeds)
Depositing User: Symplectic Publications
Date Deposited: 09 May 2011 10:16
Last Modified: 15 Sep 2014 04:00
Published Version: http://dx.doi.org/10.1016/j.jspi.2007.10.005
Status: Published
Publisher: Elsevier Science BV
Refereed: Yes
Identification Number: 10.1016/j.jspi.2007.10.005
URI: http://eprints.whiterose.ac.uk/id/eprint/42949

Actions (repository staff only: login required)