Bayesian model averaging in time-series studies of air pollution and mortality

Duncan C. Thomas, Michael Jerrett, Nino Kuenzli, Thomas Louis, Francesca Dominici, Scott Zeger, Joel Schwarz, Richard T. Burnett, Daniel Krewski, David Bates

Research output: Contribution to journalArticle

Abstract

The issue of model selection in time-series studies assessing the acute health effects from short-term exposure to ambient air pollutants has received increased scrutiny in the past 5 yr. Recently, Bayesian model averaging (BMA) has been applied to allow for uncertainty about model form in assessing the association between mortality and ambient air pollution. While BMA has the potential to allow for such uncertainties in risk estimates, Bayesian approaches in general and BMA in particular are not panaceas for model selection., Since misapplication of Bayesian methods can lead to erroneous conclusions, model selection should be informed by substantive knowledge about the environmental health processes influencing the outcome. This paper examines recent attempts to use BMA in air pollution studies to illustrate the potential benefits and limitations of the method.

Original languageEnglish (US)
Pages (from-to)311-315
Number of pages5
JournalJournal of Toxicology and Environmental Health - Part A: Current Issues
Volume70
Issue number3-4
DOIs
StatePublished - Jan 2007

Fingerprint

Bayes Theorem
Air Pollution
Air pollution
Uncertainty
Time series
Air Pollutants
Environmental Health
Mortality
Health

ASJC Scopus subject areas

  • Toxicology
  • Health, Toxicology and Mutagenesis

Cite this

Bayesian model averaging in time-series studies of air pollution and mortality. / Thomas, Duncan C.; Jerrett, Michael; Kuenzli, Nino; Louis, Thomas; Dominici, Francesca; Zeger, Scott; Schwarz, Joel; Burnett, Richard T.; Krewski, Daniel; Bates, David.

In: Journal of Toxicology and Environmental Health - Part A: Current Issues, Vol. 70, No. 3-4, 01.2007, p. 311-315.

Research output: Contribution to journalArticle

Thomas, Duncan C. ; Jerrett, Michael ; Kuenzli, Nino ; Louis, Thomas ; Dominici, Francesca ; Zeger, Scott ; Schwarz, Joel ; Burnett, Richard T. ; Krewski, Daniel ; Bates, David. / Bayesian model averaging in time-series studies of air pollution and mortality. In: Journal of Toxicology and Environmental Health - Part A: Current Issues. 2007 ; Vol. 70, No. 3-4. pp. 311-315.
@article{f8f2512805f74f00a1e21a5100e6b854,
title = "Bayesian model averaging in time-series studies of air pollution and mortality",
abstract = "The issue of model selection in time-series studies assessing the acute health effects from short-term exposure to ambient air pollutants has received increased scrutiny in the past 5 yr. Recently, Bayesian model averaging (BMA) has been applied to allow for uncertainty about model form in assessing the association between mortality and ambient air pollution. While BMA has the potential to allow for such uncertainties in risk estimates, Bayesian approaches in general and BMA in particular are not panaceas for model selection., Since misapplication of Bayesian methods can lead to erroneous conclusions, model selection should be informed by substantive knowledge about the environmental health processes influencing the outcome. This paper examines recent attempts to use BMA in air pollution studies to illustrate the potential benefits and limitations of the method.",
author = "Thomas, {Duncan C.} and Michael Jerrett and Nino Kuenzli and Thomas Louis and Francesca Dominici and Scott Zeger and Joel Schwarz and Burnett, {Richard T.} and Daniel Krewski and David Bates",
year = "2007",
month = "1",
doi = "10.1080/15287390600884941",
language = "English (US)",
volume = "70",
pages = "311--315",
journal = "Journal of Toxicology and Environmental Health - Part A: Current Issues",
issn = "1528-7394",
publisher = "Taylor and Francis Ltd.",
number = "3-4",

}

TY - JOUR

T1 - Bayesian model averaging in time-series studies of air pollution and mortality

AU - Thomas, Duncan C.

AU - Jerrett, Michael

AU - Kuenzli, Nino

AU - Louis, Thomas

AU - Dominici, Francesca

AU - Zeger, Scott

AU - Schwarz, Joel

AU - Burnett, Richard T.

AU - Krewski, Daniel

AU - Bates, David

PY - 2007/1

Y1 - 2007/1

N2 - The issue of model selection in time-series studies assessing the acute health effects from short-term exposure to ambient air pollutants has received increased scrutiny in the past 5 yr. Recently, Bayesian model averaging (BMA) has been applied to allow for uncertainty about model form in assessing the association between mortality and ambient air pollution. While BMA has the potential to allow for such uncertainties in risk estimates, Bayesian approaches in general and BMA in particular are not panaceas for model selection., Since misapplication of Bayesian methods can lead to erroneous conclusions, model selection should be informed by substantive knowledge about the environmental health processes influencing the outcome. This paper examines recent attempts to use BMA in air pollution studies to illustrate the potential benefits and limitations of the method.

AB - The issue of model selection in time-series studies assessing the acute health effects from short-term exposure to ambient air pollutants has received increased scrutiny in the past 5 yr. Recently, Bayesian model averaging (BMA) has been applied to allow for uncertainty about model form in assessing the association between mortality and ambient air pollution. While BMA has the potential to allow for such uncertainties in risk estimates, Bayesian approaches in general and BMA in particular are not panaceas for model selection., Since misapplication of Bayesian methods can lead to erroneous conclusions, model selection should be informed by substantive knowledge about the environmental health processes influencing the outcome. This paper examines recent attempts to use BMA in air pollution studies to illustrate the potential benefits and limitations of the method.

UR - http://www.scopus.com/inward/record.url?scp=33847140992&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847140992&partnerID=8YFLogxK

U2 - 10.1080/15287390600884941

DO - 10.1080/15287390600884941

M3 - Article

C2 - 17365593

AN - SCOPUS:33847140992

VL - 70

SP - 311

EP - 315

JO - Journal of Toxicology and Environmental Health - Part A: Current Issues

JF - Journal of Toxicology and Environmental Health - Part A: Current Issues

SN - 1528-7394

IS - 3-4

ER -