Correcting for bias due to mismeasured exposure in mediation analysis with a survival outcome

Chao Cheng; Donna Spiegelman; Fan Li

doi:10.1093/jrsssc/qlaf010

Correcting for bias due to mismeasured exposure in mediation analysis with a survival outcome

Chao Cheng
, Donna Spiegelman
, Fan Li

Research output: Contribution to journal › Article › peer-review

Abstract

We investigate the impact of exposure measurement error on assessing mediation with a survival outcome modelled by Cox regression. We first derive the bias formulas of natural indirect and direct effects with a rare outcome and no exposure-mediator interaction. We then develop several calibration approaches to correct for the measurement error-induced bias, and generalize our methods to accommodate a common outcome and an exposure-mediator interaction. We apply the proposed methods to analyse the Health Professionals Follow-up Study (1986-2016) and evaluate the extent to which reduced body mass index mediates the protective effect of physical activity on risk of cardiovascular diseases.

Original language	English
Pages (from-to)	969-993
Number of pages	25
Journal	Journal of the Royal Statistical Society. Series C: Applied Statistics
Volume	74
Issue number	4
DOIs	https://doi.org/10.1093/jrsssc/qlaf010
State	Published - Nov 1 2025

Keywords

Bias analysis
measurement error correction
mediation proportion
natural indirect effect
regression calibration
time-to-event data

Access to Document

10.1093/jrsssc/qlaf010

Cite this

@article{5b52458c6217469fa487ed6f5184afda,

title = "Correcting for bias due to mismeasured exposure in mediation analysis with a survival outcome",

abstract = "We investigate the impact of exposure measurement error on assessing mediation with a survival outcome modelled by Cox regression. We first derive the bias formulas of natural indirect and direct effects with a rare outcome and no exposure-mediator interaction. We then develop several calibration approaches to correct for the measurement error-induced bias, and generalize our methods to accommodate a common outcome and an exposure-mediator interaction. We apply the proposed methods to analyse the Health Professionals Follow-up Study (1986-2016) and evaluate the extent to which reduced body mass index mediates the protective effect of physical activity on risk of cardiovascular diseases.",

keywords = "Bias analysis, measurement error correction, mediation proportion, natural indirect effect, regression calibration, time-to-event data",

author = "Chao Cheng and Donna Spiegelman and Fan Li",

note = "Publisher Copyright: {\textcopyright} 2025 The Royal Statistical Society. All rights reserved. For commercial re-use, please contact [email protected] for reprints and translation rights for reprints. All other permissions can be obtained through our RightsLink service via the Permissions link on the article page on our site - for further information please contact [email protected].",

year = "2025",

month = nov,

day = "1",

doi = "10.1093/jrsssc/qlaf010",

language = "English",

volume = "74",

pages = "969--993",

journal = "Journal of the Royal Statistical Society. Series C: Applied Statistics",

issn = "0035-9254",

number = "4",

}

TY - JOUR

T1 - Correcting for bias due to mismeasured exposure in mediation analysis with a survival outcome

AU - Cheng, Chao

AU - Spiegelman, Donna

AU - Li, Fan

N1 - Publisher Copyright: © 2025 The Royal Statistical Society. All rights reserved. For commercial re-use, please contact [email protected] for reprints and translation rights for reprints. All other permissions can be obtained through our RightsLink service via the Permissions link on the article page on our site - for further information please contact [email protected].

PY - 2025/11/1

Y1 - 2025/11/1

N2 - We investigate the impact of exposure measurement error on assessing mediation with a survival outcome modelled by Cox regression. We first derive the bias formulas of natural indirect and direct effects with a rare outcome and no exposure-mediator interaction. We then develop several calibration approaches to correct for the measurement error-induced bias, and generalize our methods to accommodate a common outcome and an exposure-mediator interaction. We apply the proposed methods to analyse the Health Professionals Follow-up Study (1986-2016) and evaluate the extent to which reduced body mass index mediates the protective effect of physical activity on risk of cardiovascular diseases.

AB - We investigate the impact of exposure measurement error on assessing mediation with a survival outcome modelled by Cox regression. We first derive the bias formulas of natural indirect and direct effects with a rare outcome and no exposure-mediator interaction. We then develop several calibration approaches to correct for the measurement error-induced bias, and generalize our methods to accommodate a common outcome and an exposure-mediator interaction. We apply the proposed methods to analyse the Health Professionals Follow-up Study (1986-2016) and evaluate the extent to which reduced body mass index mediates the protective effect of physical activity on risk of cardiovascular diseases.

KW - Bias analysis

KW - measurement error correction

KW - mediation proportion

KW - natural indirect effect

KW - regression calibration

KW - time-to-event data

UR - https://www.scopus.com/pages/publications/105013672647

U2 - 10.1093/jrsssc/qlaf010

DO - 10.1093/jrsssc/qlaf010

M3 - Article

C2 - 40837827

AN - SCOPUS:105013672647

SN - 0035-9254

VL - 74

SP - 969

EP - 993

JO - Journal of the Royal Statistical Society. Series C: Applied Statistics

JF - Journal of the Royal Statistical Society. Series C: Applied Statistics

IS - 4

ER -

Correcting for bias due to mismeasured exposure in mediation analysis with a survival outcome

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this