Bayesian methods for multiple mediators: Relating principal stratification and causal mediation in the analysis of power plant emission controls

Chanmin Kim, Michael J. Daniels, Joseph W. Hogan, Christine Choirat, Corwin M. Zigler

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Emission control technologies installed on power plants are a key feature of many air pollution regulations in the US. While such regulations are predicated on the presumed relationships between emissions, ambient air pollution and human health, many of these relationships have never been empirically verified. The goal of this paper is to develop new statistical methods to quantify these relationships. We frame this problem as one of mediation analysis to evaluate the extent to which the effect of a particular control technology on ambient pollution is mediated through causal effects on power plant emissions. Since power plants emit various compounds that contribute to ambient pollution, we develop new methods for multiple intermediate variables that are measured contemporaneously, may interact with one another, and may exhibit joint mediating effects. Specifically, we propose new methods leveraging two related frameworks for causal inference in the presence of mediating variables: principal stratification and causal mediation analysis. We define principal effects based on multiple mediators, and also introduce a new decomposition of the total effect of an intervention on ambient pollution into the natural direct effect and natural indirect effects for all combinations of mediators. Both approaches are anchored to the same observed-data models, which we specify with Bayesian nonparametric techniques. We provide assumptions for estimating principal causal effects, then augment these with an additional assumption required for causal mediation analysis. The two analyses, interpreted in tandem, provide the first empirical investigation of the presumed causal pathways that motivate important air quality regulatory policies.

Original languageEnglish (US)
Pages (from-to)1927-1956
Number of pages30
JournalAnnals of Applied Statistics
Volume13
Issue number3
DOIs
StatePublished - Sep 2019

Fingerprint

Principal Stratification
Mediation
Mediator
Emission control
Power Plant
Bayesian Methods
Power plants
Pollution
Air pollution
Causal Effect
Air Pollution
Air quality
Data structures
Statistical methods
Causal Inference
Bayesian Nonparametrics
Health
Direct Effect
Air Quality
Decomposition

Keywords

  • Ambient PM
  • Bayesian nonparametrics
  • Gaussian copula
  • Multipollu-tants
  • Natural indirect effect

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation
  • Statistics, Probability and Uncertainty

Cite this

Bayesian methods for multiple mediators : Relating principal stratification and causal mediation in the analysis of power plant emission controls. / Kim, Chanmin; Daniels, Michael J.; Hogan, Joseph W.; Choirat, Christine; Zigler, Corwin M.

In: Annals of Applied Statistics, Vol. 13, No. 3, 09.2019, p. 1927-1956.

Research output: Contribution to journalArticle

@article{d33587de3166420e8380cda8bfdb444e,
title = "Bayesian methods for multiple mediators: Relating principal stratification and causal mediation in the analysis of power plant emission controls",
abstract = "Emission control technologies installed on power plants are a key feature of many air pollution regulations in the US. While such regulations are predicated on the presumed relationships between emissions, ambient air pollution and human health, many of these relationships have never been empirically verified. The goal of this paper is to develop new statistical methods to quantify these relationships. We frame this problem as one of mediation analysis to evaluate the extent to which the effect of a particular control technology on ambient pollution is mediated through causal effects on power plant emissions. Since power plants emit various compounds that contribute to ambient pollution, we develop new methods for multiple intermediate variables that are measured contemporaneously, may interact with one another, and may exhibit joint mediating effects. Specifically, we propose new methods leveraging two related frameworks for causal inference in the presence of mediating variables: principal stratification and causal mediation analysis. We define principal effects based on multiple mediators, and also introduce a new decomposition of the total effect of an intervention on ambient pollution into the natural direct effect and natural indirect effects for all combinations of mediators. Both approaches are anchored to the same observed-data models, which we specify with Bayesian nonparametric techniques. We provide assumptions for estimating principal causal effects, then augment these with an additional assumption required for causal mediation analysis. The two analyses, interpreted in tandem, provide the first empirical investigation of the presumed causal pathways that motivate important air quality regulatory policies.",
keywords = "Ambient PM, Bayesian nonparametrics, Gaussian copula, Multipollu-tants, Natural indirect effect",
author = "Chanmin Kim and Daniels, {Michael J.} and Hogan, {Joseph W.} and Christine Choirat and Zigler, {Corwin M.}",
year = "2019",
month = "9",
doi = "10.1214/19-AOAS1260",
language = "English (US)",
volume = "13",
pages = "1927--1956",
journal = "Annals of Applied Statistics",
issn = "1932-6157",
publisher = "Institute of Mathematical Statistics",
number = "3",

}

TY - JOUR

T1 - Bayesian methods for multiple mediators

T2 - Relating principal stratification and causal mediation in the analysis of power plant emission controls

AU - Kim, Chanmin

AU - Daniels, Michael J.

AU - Hogan, Joseph W.

AU - Choirat, Christine

AU - Zigler, Corwin M.

PY - 2019/9

Y1 - 2019/9

N2 - Emission control technologies installed on power plants are a key feature of many air pollution regulations in the US. While such regulations are predicated on the presumed relationships between emissions, ambient air pollution and human health, many of these relationships have never been empirically verified. The goal of this paper is to develop new statistical methods to quantify these relationships. We frame this problem as one of mediation analysis to evaluate the extent to which the effect of a particular control technology on ambient pollution is mediated through causal effects on power plant emissions. Since power plants emit various compounds that contribute to ambient pollution, we develop new methods for multiple intermediate variables that are measured contemporaneously, may interact with one another, and may exhibit joint mediating effects. Specifically, we propose new methods leveraging two related frameworks for causal inference in the presence of mediating variables: principal stratification and causal mediation analysis. We define principal effects based on multiple mediators, and also introduce a new decomposition of the total effect of an intervention on ambient pollution into the natural direct effect and natural indirect effects for all combinations of mediators. Both approaches are anchored to the same observed-data models, which we specify with Bayesian nonparametric techniques. We provide assumptions for estimating principal causal effects, then augment these with an additional assumption required for causal mediation analysis. The two analyses, interpreted in tandem, provide the first empirical investigation of the presumed causal pathways that motivate important air quality regulatory policies.

AB - Emission control technologies installed on power plants are a key feature of many air pollution regulations in the US. While such regulations are predicated on the presumed relationships between emissions, ambient air pollution and human health, many of these relationships have never been empirically verified. The goal of this paper is to develop new statistical methods to quantify these relationships. We frame this problem as one of mediation analysis to evaluate the extent to which the effect of a particular control technology on ambient pollution is mediated through causal effects on power plant emissions. Since power plants emit various compounds that contribute to ambient pollution, we develop new methods for multiple intermediate variables that are measured contemporaneously, may interact with one another, and may exhibit joint mediating effects. Specifically, we propose new methods leveraging two related frameworks for causal inference in the presence of mediating variables: principal stratification and causal mediation analysis. We define principal effects based on multiple mediators, and also introduce a new decomposition of the total effect of an intervention on ambient pollution into the natural direct effect and natural indirect effects for all combinations of mediators. Both approaches are anchored to the same observed-data models, which we specify with Bayesian nonparametric techniques. We provide assumptions for estimating principal causal effects, then augment these with an additional assumption required for causal mediation analysis. The two analyses, interpreted in tandem, provide the first empirical investigation of the presumed causal pathways that motivate important air quality regulatory policies.

KW - Ambient PM

KW - Bayesian nonparametrics

KW - Gaussian copula

KW - Multipollu-tants

KW - Natural indirect effect

UR - http://www.scopus.com/inward/record.url?scp=85073717188&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073717188&partnerID=8YFLogxK

U2 - 10.1214/19-AOAS1260

DO - 10.1214/19-AOAS1260

M3 - Article

AN - SCOPUS:85073717188

VL - 13

SP - 1927

EP - 1956

JO - Annals of Applied Statistics

JF - Annals of Applied Statistics

SN - 1932-6157

IS - 3

ER -