Analytic results on the bias due to nondifferential misclassification of a binary mediator.

Elizabeth Leigh Ogburn, Tyler J. VanderWeele

Research output: Contribution to journalArticle

Abstract

Consider a study in which the effect of a binary exposure on an outcome operates partly through a binary mediator but measurement of the mediator is nondifferentially misclassified. Suppose that an investigator wishes to estimate the direct and indirect effects of the exposure on the outcome. In this paper, the authors describe a mathematical correspondence between the empirical expressions for the natural direct effect and the effect of exposure among the unexposed standardized by a binary confounder. They then exploit this correspondence to prove that the direction of the bias due to nondifferential measurement error in estimating the natural direct and indirect effects is to overestimate the natural direct effect and underestimate the natural indirect effect.

Original languageEnglish (US)
Pages (from-to)555-561
Number of pages7
JournalAmerican Journal of Epidemiology
Volume176
Issue number6
StatePublished - Sep 15 2012
Externally publishedYes

Fingerprint

Research Personnel
Direction compound

ASJC Scopus subject areas

  • Epidemiology

Cite this

Analytic results on the bias due to nondifferential misclassification of a binary mediator. / Ogburn, Elizabeth Leigh; VanderWeele, Tyler J.

In: American Journal of Epidemiology, Vol. 176, No. 6, 15.09.2012, p. 555-561.

Research output: Contribution to journalArticle

@article{99daaaa9a2ee4adcb76bf8d4ccc32a83,
title = "Analytic results on the bias due to nondifferential misclassification of a binary mediator.",
abstract = "Consider a study in which the effect of a binary exposure on an outcome operates partly through a binary mediator but measurement of the mediator is nondifferentially misclassified. Suppose that an investigator wishes to estimate the direct and indirect effects of the exposure on the outcome. In this paper, the authors describe a mathematical correspondence between the empirical expressions for the natural direct effect and the effect of exposure among the unexposed standardized by a binary confounder. They then exploit this correspondence to prove that the direction of the bias due to nondifferential measurement error in estimating the natural direct and indirect effects is to overestimate the natural direct effect and underestimate the natural indirect effect.",
author = "Ogburn, {Elizabeth Leigh} and VanderWeele, {Tyler J.}",
year = "2012",
month = "9",
day = "15",
language = "English (US)",
volume = "176",
pages = "555--561",
journal = "American Journal of Epidemiology",
issn = "0002-9262",
publisher = "Oxford University Press",
number = "6",

}

TY - JOUR

T1 - Analytic results on the bias due to nondifferential misclassification of a binary mediator.

AU - Ogburn, Elizabeth Leigh

AU - VanderWeele, Tyler J.

PY - 2012/9/15

Y1 - 2012/9/15

N2 - Consider a study in which the effect of a binary exposure on an outcome operates partly through a binary mediator but measurement of the mediator is nondifferentially misclassified. Suppose that an investigator wishes to estimate the direct and indirect effects of the exposure on the outcome. In this paper, the authors describe a mathematical correspondence between the empirical expressions for the natural direct effect and the effect of exposure among the unexposed standardized by a binary confounder. They then exploit this correspondence to prove that the direction of the bias due to nondifferential measurement error in estimating the natural direct and indirect effects is to overestimate the natural direct effect and underestimate the natural indirect effect.

AB - Consider a study in which the effect of a binary exposure on an outcome operates partly through a binary mediator but measurement of the mediator is nondifferentially misclassified. Suppose that an investigator wishes to estimate the direct and indirect effects of the exposure on the outcome. In this paper, the authors describe a mathematical correspondence between the empirical expressions for the natural direct effect and the effect of exposure among the unexposed standardized by a binary confounder. They then exploit this correspondence to prove that the direction of the bias due to nondifferential measurement error in estimating the natural direct and indirect effects is to overestimate the natural direct effect and underestimate the natural indirect effect.

UR - http://www.scopus.com/inward/record.url?scp=84871657661&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871657661&partnerID=8YFLogxK

M3 - Article

C2 - 22930481

AN - SCOPUS:84871657661

VL - 176

SP - 555

EP - 561

JO - American Journal of Epidemiology

JF - American Journal of Epidemiology

SN - 0002-9262

IS - 6

ER -