Estimation of the correlation coefficient using the Bayesian approach and its applications for epidemiologic research

Enrique F. Schisterman, Kirsten B. Moysich, Lucinda J. England, Malla Rao

Research output: Contribution to journalArticle

Abstract

Background: The Bayesian approach is one alternative for estimating correlation coefficients in which knowledge from previous studies is incorporated to improve estimation. The purpose of this paper is to illustrate the utility of the Bayesian approach for estimating correlations using prior knowledge. Methods: The use of the hyperbolic tangent transformation (ρ = tanh ζ and r = tanh z) enables the investigator to take advantage of the conjugate properties of the normal distribution, which are expressed by combining correlation coefficients from different studies. Conclusions: One of the strengths of the proposed method is that the calculations are simple but the accuracy is maintained. Like meta-analysis, it can be seen as a method to combine different correlations from different studies.

Original languageEnglish (US)
Article number1
Pages (from-to)1-4
Number of pages4
JournalBMC Medical Research Methodology
Volume3
DOIs
StatePublished - Mar 25 2003
Externally publishedYes

Fingerprint

Bayes Theorem
Research
Normal Distribution
Meta-Analysis
Research Personnel

ASJC Scopus subject areas

  • Medicine(all)
  • Health Informatics

Cite this

Estimation of the correlation coefficient using the Bayesian approach and its applications for epidemiologic research. / Schisterman, Enrique F.; Moysich, Kirsten B.; England, Lucinda J.; Rao, Malla.

In: BMC Medical Research Methodology, Vol. 3, 1, 25.03.2003, p. 1-4.

Research output: Contribution to journalArticle

Schisterman, Enrique F. ; Moysich, Kirsten B. ; England, Lucinda J. ; Rao, Malla. / Estimation of the correlation coefficient using the Bayesian approach and its applications for epidemiologic research. In: BMC Medical Research Methodology. 2003 ; Vol. 3. pp. 1-4.
@article{566d6c2d0bb04f71beadcab5de0a4701,
title = "Estimation of the correlation coefficient using the Bayesian approach and its applications for epidemiologic research",
abstract = "Background: The Bayesian approach is one alternative for estimating correlation coefficients in which knowledge from previous studies is incorporated to improve estimation. The purpose of this paper is to illustrate the utility of the Bayesian approach for estimating correlations using prior knowledge. Methods: The use of the hyperbolic tangent transformation (ρ = tanh ζ and r = tanh z) enables the investigator to take advantage of the conjugate properties of the normal distribution, which are expressed by combining correlation coefficients from different studies. Conclusions: One of the strengths of the proposed method is that the calculations are simple but the accuracy is maintained. Like meta-analysis, it can be seen as a method to combine different correlations from different studies.",
author = "Schisterman, {Enrique F.} and Moysich, {Kirsten B.} and England, {Lucinda J.} and Malla Rao",
year = "2003",
month = "3",
day = "25",
doi = "10.1186/1471-2288-3-1",
language = "English (US)",
volume = "3",
pages = "1--4",
journal = "BMC Medical Research Methodology",
issn = "1471-2288",
publisher = "BioMed Central",

}

TY - JOUR

T1 - Estimation of the correlation coefficient using the Bayesian approach and its applications for epidemiologic research

AU - Schisterman, Enrique F.

AU - Moysich, Kirsten B.

AU - England, Lucinda J.

AU - Rao, Malla

PY - 2003/3/25

Y1 - 2003/3/25

N2 - Background: The Bayesian approach is one alternative for estimating correlation coefficients in which knowledge from previous studies is incorporated to improve estimation. The purpose of this paper is to illustrate the utility of the Bayesian approach for estimating correlations using prior knowledge. Methods: The use of the hyperbolic tangent transformation (ρ = tanh ζ and r = tanh z) enables the investigator to take advantage of the conjugate properties of the normal distribution, which are expressed by combining correlation coefficients from different studies. Conclusions: One of the strengths of the proposed method is that the calculations are simple but the accuracy is maintained. Like meta-analysis, it can be seen as a method to combine different correlations from different studies.

AB - Background: The Bayesian approach is one alternative for estimating correlation coefficients in which knowledge from previous studies is incorporated to improve estimation. The purpose of this paper is to illustrate the utility of the Bayesian approach for estimating correlations using prior knowledge. Methods: The use of the hyperbolic tangent transformation (ρ = tanh ζ and r = tanh z) enables the investigator to take advantage of the conjugate properties of the normal distribution, which are expressed by combining correlation coefficients from different studies. Conclusions: One of the strengths of the proposed method is that the calculations are simple but the accuracy is maintained. Like meta-analysis, it can be seen as a method to combine different correlations from different studies.

UR - http://www.scopus.com/inward/record.url?scp=2942731717&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2942731717&partnerID=8YFLogxK

U2 - 10.1186/1471-2288-3-1

DO - 10.1186/1471-2288-3-1

M3 - Article

AN - SCOPUS:2942731717

VL - 3

SP - 1

EP - 4

JO - BMC Medical Research Methodology

JF - BMC Medical Research Methodology

SN - 1471-2288

M1 - 1

ER -