A Bayesian approach estimating treatment effects on biomarkers containing zeros with detection limits

Haitao Chu, Lei Nie, Thomas W Kensler

Research output: Contribution to journalArticle

Abstract

Often in randomized clinical trials and observational studies in occupational and environmental health, a non-negative continuously distributed response variable denoting some metabolites of environmental toxicants is measured in treatment and control groups. When observations occur in both unexposed and exposed subjects, the biomarker measurement can be bimodally distributed with an extra spike at zero reflecting those unexposed. In the presence of left censoring due to values falling below biomarker assay detection limits, those unexposed with true zeros are indistinguishable from those exposed with left-censored values. Since interventions usually do not enhance or eliminate exposure, they do not have any impact on those unexposed. Thus, only the subset of individuals who are exposed should be used to make comparisons to estimate the effect of interventions. In this article, we present Bayesian approaches using non-standard mixture distributions to account for true zeros. The performance of the proposed Bayesian methods is compared with the maximum likelihood methods presented in Chu et al. (Stat. Med. 2005; 24:2053-2067) through simulation studies and a randomized chemoprevention trial conducted in Qidong, People's Republic of China.

Original languageEnglish (US)
Pages (from-to)2497-2508
Number of pages12
JournalStatistics in Medicine
Volume27
Issue number13
DOIs
StatePublished - Jun 15 2008

Fingerprint

Detection Limit
Bayes Theorem
Biomarkers
Treatment Effects
Bayesian Approach
Limit of Detection
Environmental Health
Chemoprevention
Zero
Occupational Health
Left Censoring
Toxicants
Observational Studies
Randomized Clinical Trial
China
Mixture Distribution
Randomized Trial
Observational Study
Randomized Controlled Trials
Maximum Likelihood Method

Keywords

  • Bayesian methods
  • Clinical trials
  • Left censoring
  • Mixture models
  • Model selection

ASJC Scopus subject areas

  • Epidemiology

Cite this

A Bayesian approach estimating treatment effects on biomarkers containing zeros with detection limits. / Chu, Haitao; Nie, Lei; Kensler, Thomas W.

In: Statistics in Medicine, Vol. 27, No. 13, 15.06.2008, p. 2497-2508.

Research output: Contribution to journalArticle

@article{8db5220550644ea2b54257118a98a241,
title = "A Bayesian approach estimating treatment effects on biomarkers containing zeros with detection limits",
abstract = "Often in randomized clinical trials and observational studies in occupational and environmental health, a non-negative continuously distributed response variable denoting some metabolites of environmental toxicants is measured in treatment and control groups. When observations occur in both unexposed and exposed subjects, the biomarker measurement can be bimodally distributed with an extra spike at zero reflecting those unexposed. In the presence of left censoring due to values falling below biomarker assay detection limits, those unexposed with true zeros are indistinguishable from those exposed with left-censored values. Since interventions usually do not enhance or eliminate exposure, they do not have any impact on those unexposed. Thus, only the subset of individuals who are exposed should be used to make comparisons to estimate the effect of interventions. In this article, we present Bayesian approaches using non-standard mixture distributions to account for true zeros. The performance of the proposed Bayesian methods is compared with the maximum likelihood methods presented in Chu et al. (Stat. Med. 2005; 24:2053-2067) through simulation studies and a randomized chemoprevention trial conducted in Qidong, People's Republic of China.",
keywords = "Bayesian methods, Clinical trials, Left censoring, Mixture models, Model selection",
author = "Haitao Chu and Lei Nie and Kensler, {Thomas W}",
year = "2008",
month = "6",
day = "15",
doi = "10.1002/sim.3170",
language = "English (US)",
volume = "27",
pages = "2497--2508",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "13",

}

TY - JOUR

T1 - A Bayesian approach estimating treatment effects on biomarkers containing zeros with detection limits

AU - Chu, Haitao

AU - Nie, Lei

AU - Kensler, Thomas W

PY - 2008/6/15

Y1 - 2008/6/15

N2 - Often in randomized clinical trials and observational studies in occupational and environmental health, a non-negative continuously distributed response variable denoting some metabolites of environmental toxicants is measured in treatment and control groups. When observations occur in both unexposed and exposed subjects, the biomarker measurement can be bimodally distributed with an extra spike at zero reflecting those unexposed. In the presence of left censoring due to values falling below biomarker assay detection limits, those unexposed with true zeros are indistinguishable from those exposed with left-censored values. Since interventions usually do not enhance or eliminate exposure, they do not have any impact on those unexposed. Thus, only the subset of individuals who are exposed should be used to make comparisons to estimate the effect of interventions. In this article, we present Bayesian approaches using non-standard mixture distributions to account for true zeros. The performance of the proposed Bayesian methods is compared with the maximum likelihood methods presented in Chu et al. (Stat. Med. 2005; 24:2053-2067) through simulation studies and a randomized chemoprevention trial conducted in Qidong, People's Republic of China.

AB - Often in randomized clinical trials and observational studies in occupational and environmental health, a non-negative continuously distributed response variable denoting some metabolites of environmental toxicants is measured in treatment and control groups. When observations occur in both unexposed and exposed subjects, the biomarker measurement can be bimodally distributed with an extra spike at zero reflecting those unexposed. In the presence of left censoring due to values falling below biomarker assay detection limits, those unexposed with true zeros are indistinguishable from those exposed with left-censored values. Since interventions usually do not enhance or eliminate exposure, they do not have any impact on those unexposed. Thus, only the subset of individuals who are exposed should be used to make comparisons to estimate the effect of interventions. In this article, we present Bayesian approaches using non-standard mixture distributions to account for true zeros. The performance of the proposed Bayesian methods is compared with the maximum likelihood methods presented in Chu et al. (Stat. Med. 2005; 24:2053-2067) through simulation studies and a randomized chemoprevention trial conducted in Qidong, People's Republic of China.

KW - Bayesian methods

KW - Clinical trials

KW - Left censoring

KW - Mixture models

KW - Model selection

UR - http://www.scopus.com/inward/record.url?scp=44949176565&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44949176565&partnerID=8YFLogxK

U2 - 10.1002/sim.3170

DO - 10.1002/sim.3170

M3 - Article

C2 - 18167630

AN - SCOPUS:44949176565

VL - 27

SP - 2497

EP - 2508

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 13

ER -