Multivariate left-censored Bayesian modeling for predicting exposure using multiple chemical predictors

Caroline P. Groth, Sudipto Banerjee, Gurumurthy Ramachandran, Mark R. Stenzel, Patricia A. Stewart

Research output: Contribution to journalArticle

Abstract

Environmental health exposures to airborne chemicals often originate from chemical mixtures. Environmental health professionals may be interested in assessing exposure to one or more of the chemicals in these mixtures, but often, exposure measurement data are not available, either because measurements were not collected/assessed for all exposure scenarios of interest or because some of the measurements were below the analytical methods' limits of detection (i.e., censored). In some cases, based on chemical laws, two or more components may have linear relationships with one another, whether in single or multiple mixtures. Although bivariate analyses can be used if the correlation is high, correlations are often low. To serve this need, this paper develops a multivariate framework for assessing exposure using relationships of the chemicals present in these mixtures. This framework accounts for censored measurements in all chemicals, allowing us to develop unbiased exposure estimates. We assessed our model's performance against simpler models at a variety of censoring levels and assessed our model's 95% coverage. We applied our model to assess vapor exposure from measurements of three chemicals in crude oil taken on the Ocean Intervention III during the Deepwater Horizon oil spill response and cleanup.

Original languageEnglish (US)
Article numbere2505
JournalEnvironmetrics
Volume29
Issue number4
DOIs
StatePublished - Jun 1 2018

Fingerprint

Bayesian Modeling
Predictors
modeling
Health
oil spill response
Oil Spill
Performance Model
Censoring
cleanup
exposure
chemical
Analytical Methods
Ocean
crude oil
Horizon
analytical method
Coverage
Model
Scenarios
ocean

Keywords

  • chemical mixtures
  • correlations
  • Deepwater Horizon oil spill
  • exposure assessment

ASJC Scopus subject areas

  • Statistics and Probability
  • Ecological Modeling

Cite this

Multivariate left-censored Bayesian modeling for predicting exposure using multiple chemical predictors. / Groth, Caroline P.; Banerjee, Sudipto; Ramachandran, Gurumurthy; Stenzel, Mark R.; Stewart, Patricia A.

In: Environmetrics, Vol. 29, No. 4, e2505, 01.06.2018.

Research output: Contribution to journalArticle

Groth, Caroline P. ; Banerjee, Sudipto ; Ramachandran, Gurumurthy ; Stenzel, Mark R. ; Stewart, Patricia A. / Multivariate left-censored Bayesian modeling for predicting exposure using multiple chemical predictors. In: Environmetrics. 2018 ; Vol. 29, No. 4.
@article{2916a0d8f8434c32bfd4094281567f41,
title = "Multivariate left-censored Bayesian modeling for predicting exposure using multiple chemical predictors",
abstract = "Environmental health exposures to airborne chemicals often originate from chemical mixtures. Environmental health professionals may be interested in assessing exposure to one or more of the chemicals in these mixtures, but often, exposure measurement data are not available, either because measurements were not collected/assessed for all exposure scenarios of interest or because some of the measurements were below the analytical methods' limits of detection (i.e., censored). In some cases, based on chemical laws, two or more components may have linear relationships with one another, whether in single or multiple mixtures. Although bivariate analyses can be used if the correlation is high, correlations are often low. To serve this need, this paper develops a multivariate framework for assessing exposure using relationships of the chemicals present in these mixtures. This framework accounts for censored measurements in all chemicals, allowing us to develop unbiased exposure estimates. We assessed our model's performance against simpler models at a variety of censoring levels and assessed our model's 95{\%} coverage. We applied our model to assess vapor exposure from measurements of three chemicals in crude oil taken on the Ocean Intervention III during the Deepwater Horizon oil spill response and cleanup.",
keywords = "chemical mixtures, correlations, Deepwater Horizon oil spill, exposure assessment",
author = "Groth, {Caroline P.} and Sudipto Banerjee and Gurumurthy Ramachandran and Stenzel, {Mark R.} and Stewart, {Patricia A.}",
year = "2018",
month = "6",
day = "1",
doi = "10.1002/env.2505",
language = "English (US)",
volume = "29",
journal = "Environmetrics",
issn = "1180-4009",
publisher = "John Wiley and Sons Ltd",
number = "4",

}

TY - JOUR

T1 - Multivariate left-censored Bayesian modeling for predicting exposure using multiple chemical predictors

AU - Groth, Caroline P.

AU - Banerjee, Sudipto

AU - Ramachandran, Gurumurthy

AU - Stenzel, Mark R.

AU - Stewart, Patricia A.

PY - 2018/6/1

Y1 - 2018/6/1

N2 - Environmental health exposures to airborne chemicals often originate from chemical mixtures. Environmental health professionals may be interested in assessing exposure to one or more of the chemicals in these mixtures, but often, exposure measurement data are not available, either because measurements were not collected/assessed for all exposure scenarios of interest or because some of the measurements were below the analytical methods' limits of detection (i.e., censored). In some cases, based on chemical laws, two or more components may have linear relationships with one another, whether in single or multiple mixtures. Although bivariate analyses can be used if the correlation is high, correlations are often low. To serve this need, this paper develops a multivariate framework for assessing exposure using relationships of the chemicals present in these mixtures. This framework accounts for censored measurements in all chemicals, allowing us to develop unbiased exposure estimates. We assessed our model's performance against simpler models at a variety of censoring levels and assessed our model's 95% coverage. We applied our model to assess vapor exposure from measurements of three chemicals in crude oil taken on the Ocean Intervention III during the Deepwater Horizon oil spill response and cleanup.

AB - Environmental health exposures to airborne chemicals often originate from chemical mixtures. Environmental health professionals may be interested in assessing exposure to one or more of the chemicals in these mixtures, but often, exposure measurement data are not available, either because measurements were not collected/assessed for all exposure scenarios of interest or because some of the measurements were below the analytical methods' limits of detection (i.e., censored). In some cases, based on chemical laws, two or more components may have linear relationships with one another, whether in single or multiple mixtures. Although bivariate analyses can be used if the correlation is high, correlations are often low. To serve this need, this paper develops a multivariate framework for assessing exposure using relationships of the chemicals present in these mixtures. This framework accounts for censored measurements in all chemicals, allowing us to develop unbiased exposure estimates. We assessed our model's performance against simpler models at a variety of censoring levels and assessed our model's 95% coverage. We applied our model to assess vapor exposure from measurements of three chemicals in crude oil taken on the Ocean Intervention III during the Deepwater Horizon oil spill response and cleanup.

KW - chemical mixtures

KW - correlations

KW - Deepwater Horizon oil spill

KW - exposure assessment

UR - http://www.scopus.com/inward/record.url?scp=85048048284&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048048284&partnerID=8YFLogxK

U2 - 10.1002/env.2505

DO - 10.1002/env.2505

M3 - Article

C2 - 30467454

AN - SCOPUS:85048048284

VL - 29

JO - Environmetrics

JF - Environmetrics

SN - 1180-4009

IS - 4

M1 - e2505

ER -