Measurement error correction and sensitivity analysis in longitudinal dietary intervention studies using an external validation study

Juned Siddique; Michael J. Daniels; Raymond J. Carroll; Trivellore E. Raghunathan; Elizabeth A. Stuart; Laurence S. Freedman

doi:10.1111/biom.13044

Measurement error correction and sensitivity analysis in longitudinal dietary intervention studies using an external validation study

Juned Siddique, Michael J. Daniels, Raymond J. Carroll, Trivellore E. Raghunathan, Elizabeth A. Stuart, Laurence S. Freedman

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

7 Scopus citations

Abstract

In lifestyle intervention trials, where the goal is to change a participant's weight or modify their eating behavior, self-reported diet is a longitudinal outcome variable that is subject to measurement error. We propose a statistical framework for correcting for measurement error in longitudinal self-reported dietary data by combining intervention data with auxiliary data from an external biomarker validation study where both self-reported and recovery biomarkers of dietary intake are available. In this setting, dietary intake measured without error in the intervention trial is missing data and multiple imputation is used to fill in the missing measurements. Since most validation studies are cross-sectional, they do not contain information on whether the nature of the measurement error changes over time or differs between treatment and control groups. We use sensitivity analyses to address the influence of these unverifiable assumptions involving the measurement error process and how they affect inferences regarding the effect of treatment. We apply our methods to self-reported sodium intake from the PREMIER study, a multi-component lifestyle intervention trial.

Original language	English
Pages (from-to)	927-937
Number of pages	11
Journal	Biometrics
Volume	75
Issue number	3
DOIs	https://doi.org/10.1111/biom.13044
State	Published - 1 Sep 2019
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2019 International Biometric Society

Funding

Siddique and Stuart's work was supported by NIH R01 HL127491. Daniels’ work was partially supported by NIH CA183854. Carroll's research was supported by a grant from the National Cancer Institute (U01-CA057030). Additional supporting information including synthetic versions of the OPEN and PREMIER data sets and R functions to implement the methods used in their analysis in Section 6 may be found online in the Supporting Information section at the end of the article.

Funders	Funder number
National Institutes of Health	CA183854, R01 HL127491
National Cancer Institute	U01CA057030

Keywords

24-hour dietary recall
Multiple imputation
recovery biomarker
sodium intake

Access to Document

10.1111/biom.13044

Cite this

@article{22e1f4db2c98476681e34e03d06c2146,

title = "Measurement error correction and sensitivity analysis in longitudinal dietary intervention studies using an external validation study",

abstract = "In lifestyle intervention trials, where the goal is to change a participant's weight or modify their eating behavior, self-reported diet is a longitudinal outcome variable that is subject to measurement error. We propose a statistical framework for correcting for measurement error in longitudinal self-reported dietary data by combining intervention data with auxiliary data from an external biomarker validation study where both self-reported and recovery biomarkers of dietary intake are available. In this setting, dietary intake measured without error in the intervention trial is missing data and multiple imputation is used to fill in the missing measurements. Since most validation studies are cross-sectional, they do not contain information on whether the nature of the measurement error changes over time or differs between treatment and control groups. We use sensitivity analyses to address the influence of these unverifiable assumptions involving the measurement error process and how they affect inferences regarding the effect of treatment. We apply our methods to self-reported sodium intake from the PREMIER study, a multi-component lifestyle intervention trial.",

keywords = "24-hour dietary recall, Multiple imputation, recovery biomarker, sodium intake",

author = "Juned Siddique and Daniels, {Michael J.} and Carroll, {Raymond J.} and Raghunathan, {Trivellore E.} and Stuart, {Elizabeth A.} and Freedman, {Laurence S.}",

note = "Publisher Copyright: {\textcopyright} 2019 International Biometric Society",

year = "2019",

month = sep,

day = "1",

doi = "10.1111/biom.13044",

language = "אנגלית",

volume = "75",

pages = "927--937",

journal = "Biometrics",

issn = "0006-341X",

publisher = "Oxford University Press",

number = "3",

}

TY - JOUR

T1 - Measurement error correction and sensitivity analysis in longitudinal dietary intervention studies using an external validation study

AU - Siddique, Juned

AU - Daniels, Michael J.

AU - Carroll, Raymond J.

AU - Raghunathan, Trivellore E.

AU - Stuart, Elizabeth A.

AU - Freedman, Laurence S.

PY - 2019/9/1

Y1 - 2019/9/1

N2 - In lifestyle intervention trials, where the goal is to change a participant's weight or modify their eating behavior, self-reported diet is a longitudinal outcome variable that is subject to measurement error. We propose a statistical framework for correcting for measurement error in longitudinal self-reported dietary data by combining intervention data with auxiliary data from an external biomarker validation study where both self-reported and recovery biomarkers of dietary intake are available. In this setting, dietary intake measured without error in the intervention trial is missing data and multiple imputation is used to fill in the missing measurements. Since most validation studies are cross-sectional, they do not contain information on whether the nature of the measurement error changes over time or differs between treatment and control groups. We use sensitivity analyses to address the influence of these unverifiable assumptions involving the measurement error process and how they affect inferences regarding the effect of treatment. We apply our methods to self-reported sodium intake from the PREMIER study, a multi-component lifestyle intervention trial.

AB - In lifestyle intervention trials, where the goal is to change a participant's weight or modify their eating behavior, self-reported diet is a longitudinal outcome variable that is subject to measurement error. We propose a statistical framework for correcting for measurement error in longitudinal self-reported dietary data by combining intervention data with auxiliary data from an external biomarker validation study where both self-reported and recovery biomarkers of dietary intake are available. In this setting, dietary intake measured without error in the intervention trial is missing data and multiple imputation is used to fill in the missing measurements. Since most validation studies are cross-sectional, they do not contain information on whether the nature of the measurement error changes over time or differs between treatment and control groups. We use sensitivity analyses to address the influence of these unverifiable assumptions involving the measurement error process and how they affect inferences regarding the effect of treatment. We apply our methods to self-reported sodium intake from the PREMIER study, a multi-component lifestyle intervention trial.

KW - 24-hour dietary recall

KW - Multiple imputation

KW - recovery biomarker

KW - sodium intake

UR - http://www.scopus.com/inward/record.url?scp=85063944932&partnerID=8YFLogxK

U2 - 10.1111/biom.13044

DO - 10.1111/biom.13044

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

C2 - 30724332

AN - SCOPUS:85063944932

SN - 0006-341X

VL - 75

SP - 927

EP - 937

JO - Biometrics

JF - Biometrics

IS - 3

ER -

Measurement error correction and sensitivity analysis in longitudinal dietary intervention studies using an external validation study

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this