Kernel estimation of relative risk

Julia E. Kelsall, Peter J. Diggle

Research output: Contribution to journalArticle

Abstract

Estimation of a relative risk function using a ratio of two kernel density estimates is considered, concentrating on the problem of choosing the smoothing parameters. A cross-validation method is proposed, compared with a range of other methods and found to be an improvement when the actual risk is close to constant. In particular, theoretical and empirical comparisons demonstrate the advantage of choosing the smoothing parameters jointly. The methodology was motivated by a class of problems in environmental epidemiology, and an application in this area is described.

Original languageEnglish (US)
Pages (from-to)3-16
Number of pages14
JournalBernoulli
Volume1
Issue number1-2
DOIs
StatePublished - 1995
Externally publishedYes

Fingerprint

Kernel Estimation
Relative Risk
Smoothing Parameter
Environmental Epidemiology
Kernel Density Estimate
Risk Function
Cross-validation
Methodology
Range of data
Demonstrate
Class

Keywords

  • Cross-validation
  • Epidemiology
  • Kernel density estimation
  • Smoothing parameters

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

Kelsall, J. E., & Diggle, P. J. (1995). Kernel estimation of relative risk. Bernoulli, 1(1-2), 3-16. https://doi.org/10.3150/bj/1186078359

Kernel estimation of relative risk. / Kelsall, Julia E.; Diggle, Peter J.

In: Bernoulli, Vol. 1, No. 1-2, 1995, p. 3-16.

Research output: Contribution to journalArticle

Kelsall, JE & Diggle, PJ 1995, 'Kernel estimation of relative risk', Bernoulli, vol. 1, no. 1-2, pp. 3-16. https://doi.org/10.3150/bj/1186078359
Kelsall, Julia E. ; Diggle, Peter J. / Kernel estimation of relative risk. In: Bernoulli. 1995 ; Vol. 1, No. 1-2. pp. 3-16.
@article{2713cba0ab9e4171ade3a7d618f98765,
title = "Kernel estimation of relative risk",
abstract = "Estimation of a relative risk function using a ratio of two kernel density estimates is considered, concentrating on the problem of choosing the smoothing parameters. A cross-validation method is proposed, compared with a range of other methods and found to be an improvement when the actual risk is close to constant. In particular, theoretical and empirical comparisons demonstrate the advantage of choosing the smoothing parameters jointly. The methodology was motivated by a class of problems in environmental epidemiology, and an application in this area is described.",
keywords = "Cross-validation, Epidemiology, Kernel density estimation, Smoothing parameters",
author = "Kelsall, {Julia E.} and Diggle, {Peter J.}",
year = "1995",
doi = "10.3150/bj/1186078359",
language = "English (US)",
volume = "1",
pages = "3--16",
journal = "Bernoulli",
issn = "1350-7265",
publisher = "International Statistical Institute",
number = "1-2",

}

TY - JOUR

T1 - Kernel estimation of relative risk

AU - Kelsall, Julia E.

AU - Diggle, Peter J.

PY - 1995

Y1 - 1995

N2 - Estimation of a relative risk function using a ratio of two kernel density estimates is considered, concentrating on the problem of choosing the smoothing parameters. A cross-validation method is proposed, compared with a range of other methods and found to be an improvement when the actual risk is close to constant. In particular, theoretical and empirical comparisons demonstrate the advantage of choosing the smoothing parameters jointly. The methodology was motivated by a class of problems in environmental epidemiology, and an application in this area is described.

AB - Estimation of a relative risk function using a ratio of two kernel density estimates is considered, concentrating on the problem of choosing the smoothing parameters. A cross-validation method is proposed, compared with a range of other methods and found to be an improvement when the actual risk is close to constant. In particular, theoretical and empirical comparisons demonstrate the advantage of choosing the smoothing parameters jointly. The methodology was motivated by a class of problems in environmental epidemiology, and an application in this area is described.

KW - Cross-validation

KW - Epidemiology

KW - Kernel density estimation

KW - Smoothing parameters

UR - http://www.scopus.com/inward/record.url?scp=84972526998&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84972526998&partnerID=8YFLogxK

U2 - 10.3150/bj/1186078359

DO - 10.3150/bj/1186078359

M3 - Article

VL - 1

SP - 3

EP - 16

JO - Bernoulli

JF - Bernoulli

SN - 1350-7265

IS - 1-2

ER -