High order data sharpening for density estimation

Authors: Hall P.¹; Minnotte M.C.²

Source: Journal of the Royal Statistical Society: Series B (Statistical Methodology), Volume 64, Number 1, 2002 , pp. 141-157(17)

Publisher: Wiley-Blackwell

Buy & download fulltext article:

The full text article is temporarily unavailable.

We apologise for the inconvenience. Please try again later.

Abstract:

It is shown that data sharpening can be used to produce density estimators that enjoy arbitrarily high orders of bias reduction. Practical advantages of this approach, relative to competing methods, are demonstrated. They include the sheer simplicity of the estimators, which makes code for computing them particularly easy to write, very good mean-squared error performance, reduced ‘wiggliness’ of estimates and greater robustness against undersmoothing.

Keywords: Bandwidth; Bias reduction; Kernel methods; Local polynomial methods; Mean-squared error; Nonparametric curve estimation; Transformation methods; Wiggliness

Language: English

Document Type: Research article

Affiliations: 1: Australian National University, Canberra, AustraliaPeter.Hall@maths.anu.edu.au 2: Utah State University, Logan, USA, and Australian National University, Canberra, Australia

Publication date: 2002-01-01