Some improvements on a boundary corrected kernel density estimator

R. J. Karunamuni, S. Zhang

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

In a very interesting article, Zhang et al. [1999. An improved estimator of the density function at the boundary. J. Amer. Statist. Assoc. 448, 1231-1241] proposed a new method of boundary correction for kernel density estimation. Their technique is a kind of generalized reflection method involving reflecting a transformation of the data. In this paper, we present a modification to their estimator. We observe that this modification significantly improves the asymptotic bias and variance of their estimator.

Original languageEnglish (US)
Pages (from-to)499-507
Number of pages9
JournalStatistics and Probability Letters
Volume78
Issue number5
DOIs
StatePublished - Apr 1 2008

Fingerprint

Kernel Density Estimator
Estimator
Asymptotic Bias
Kernel Density Estimation
Asymptotic Variance
Density Function
Kernel density

Keywords

  • Density estimation
  • Kernel density estimation
  • Mean squared error
  • Reflection
  • Transformation boundary effects

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Some improvements on a boundary corrected kernel density estimator. / Karunamuni, R. J.; Zhang, S.

In: Statistics and Probability Letters, Vol. 78, No. 5, 01.04.2008, p. 499-507.

Research output: Contribution to journalArticle

Karunamuni, R. J. ; Zhang, S. / Some improvements on a boundary corrected kernel density estimator. In: Statistics and Probability Letters. 2008 ; Vol. 78, No. 5. pp. 499-507.
@article{8653c74b231949b889e68561f42fff66,
title = "Some improvements on a boundary corrected kernel density estimator",
abstract = "In a very interesting article, Zhang et al. [1999. An improved estimator of the density function at the boundary. J. Amer. Statist. Assoc. 448, 1231-1241] proposed a new method of boundary correction for kernel density estimation. Their technique is a kind of generalized reflection method involving reflecting a transformation of the data. In this paper, we present a modification to their estimator. We observe that this modification significantly improves the asymptotic bias and variance of their estimator.",
keywords = "Density estimation, Kernel density estimation, Mean squared error, Reflection, Transformation boundary effects",
author = "Karunamuni, {R. J.} and S. Zhang",
year = "2008",
month = "4",
day = "1",
doi = "10.1016/j.spl.2007.09.002",
language = "English (US)",
volume = "78",
pages = "499--507",
journal = "Statistics and Probability Letters",
issn = "0167-7152",
publisher = "Elsevier",
number = "5",

}

TY - JOUR

T1 - Some improvements on a boundary corrected kernel density estimator

AU - Karunamuni, R. J.

AU - Zhang, S.

PY - 2008/4/1

Y1 - 2008/4/1

N2 - In a very interesting article, Zhang et al. [1999. An improved estimator of the density function at the boundary. J. Amer. Statist. Assoc. 448, 1231-1241] proposed a new method of boundary correction for kernel density estimation. Their technique is a kind of generalized reflection method involving reflecting a transformation of the data. In this paper, we present a modification to their estimator. We observe that this modification significantly improves the asymptotic bias and variance of their estimator.

AB - In a very interesting article, Zhang et al. [1999. An improved estimator of the density function at the boundary. J. Amer. Statist. Assoc. 448, 1231-1241] proposed a new method of boundary correction for kernel density estimation. Their technique is a kind of generalized reflection method involving reflecting a transformation of the data. In this paper, we present a modification to their estimator. We observe that this modification significantly improves the asymptotic bias and variance of their estimator.

KW - Density estimation

KW - Kernel density estimation

KW - Mean squared error

KW - Reflection

KW - Transformation boundary effects

UR - http://www.scopus.com/inward/record.url?scp=40449102200&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=40449102200&partnerID=8YFLogxK

U2 - 10.1016/j.spl.2007.09.002

DO - 10.1016/j.spl.2007.09.002

M3 - Article

AN - SCOPUS:40449102200

VL - 78

SP - 499

EP - 507

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

SN - 0167-7152

IS - 5

ER -