Sensitivity Plots for Confounder Bias in the Single Mediator Model

Matthew G. Cox, Yasemin Kisbu-Sakarya, Milica Miočević, David Mackinnon

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Background: Causal inference continues to be a critical aspect of evaluation research. Recent research in causal inference for statistical mediation has focused on addressing the sequential ignorability assumption; specifically, that there is no confounding between the mediator and the outcome variable. Objectives: This article compares and contrasts three different methods for assessing sensitivity to confounding and describes the graphical depiction of these methods. Design: Two types of data were used to fully examine the plots for sensitivity analysis. The first type was generated data from a single mediator model with a confounder influencing both the mediator and the outcome variable. The second was data from an actual intervention study. With both types of data, situations are examined where confounding has a large effect and a small effect. Subjects: The nonsimulated data were from a large intervention study to decrease intentions to use steroids among high school football players. We demonstrate one situation where confounding is likely and another situation where confounding is unlikely. Conclusions: We discuss how these methods could be implemented in future mediation studies as well as the limitations and future directions for these methods.

Original languageEnglish (US)
Pages (from-to)405-431
Number of pages27
JournalEvaluation Review
Volume37
Issue number5
DOIs
StatePublished - 2014

Fingerprint

trend
mediation
evaluation research
Mediator
Plot
school
Mediation
Causal Inference
Football
Research Evaluation
Intentions
Steroids
High School
Players
Sensitivity Analysis

Keywords

  • causal inference
  • confounder bias
  • indirect effects
  • mediation
  • sensitivity analysis

ASJC Scopus subject areas

  • Social Sciences(all)
  • Arts and Humanities (miscellaneous)

Cite this

Sensitivity Plots for Confounder Bias in the Single Mediator Model. / Cox, Matthew G.; Kisbu-Sakarya, Yasemin; Miočević, Milica; Mackinnon, David.

In: Evaluation Review, Vol. 37, No. 5, 2014, p. 405-431.

Research output: Contribution to journalArticle

Cox, Matthew G. ; Kisbu-Sakarya, Yasemin ; Miočević, Milica ; Mackinnon, David. / Sensitivity Plots for Confounder Bias in the Single Mediator Model. In: Evaluation Review. 2014 ; Vol. 37, No. 5. pp. 405-431.
@article{f9f948e1fb5d4453aedfc364aab6f0c7,
title = "Sensitivity Plots for Confounder Bias in the Single Mediator Model",
abstract = "Background: Causal inference continues to be a critical aspect of evaluation research. Recent research in causal inference for statistical mediation has focused on addressing the sequential ignorability assumption; specifically, that there is no confounding between the mediator and the outcome variable. Objectives: This article compares and contrasts three different methods for assessing sensitivity to confounding and describes the graphical depiction of these methods. Design: Two types of data were used to fully examine the plots for sensitivity analysis. The first type was generated data from a single mediator model with a confounder influencing both the mediator and the outcome variable. The second was data from an actual intervention study. With both types of data, situations are examined where confounding has a large effect and a small effect. Subjects: The nonsimulated data were from a large intervention study to decrease intentions to use steroids among high school football players. We demonstrate one situation where confounding is likely and another situation where confounding is unlikely. Conclusions: We discuss how these methods could be implemented in future mediation studies as well as the limitations and future directions for these methods.",
keywords = "causal inference, confounder bias, indirect effects, mediation, sensitivity analysis",
author = "Cox, {Matthew G.} and Yasemin Kisbu-Sakarya and Milica Miočević and David Mackinnon",
year = "2014",
doi = "10.1177/0193841X14524576",
language = "English (US)",
volume = "37",
pages = "405--431",
journal = "Evaluation Review",
issn = "0193-841X",
publisher = "SAGE Publications Inc.",
number = "5",

}

TY - JOUR

T1 - Sensitivity Plots for Confounder Bias in the Single Mediator Model

AU - Cox, Matthew G.

AU - Kisbu-Sakarya, Yasemin

AU - Miočević, Milica

AU - Mackinnon, David

PY - 2014

Y1 - 2014

N2 - Background: Causal inference continues to be a critical aspect of evaluation research. Recent research in causal inference for statistical mediation has focused on addressing the sequential ignorability assumption; specifically, that there is no confounding between the mediator and the outcome variable. Objectives: This article compares and contrasts three different methods for assessing sensitivity to confounding and describes the graphical depiction of these methods. Design: Two types of data were used to fully examine the plots for sensitivity analysis. The first type was generated data from a single mediator model with a confounder influencing both the mediator and the outcome variable. The second was data from an actual intervention study. With both types of data, situations are examined where confounding has a large effect and a small effect. Subjects: The nonsimulated data were from a large intervention study to decrease intentions to use steroids among high school football players. We demonstrate one situation where confounding is likely and another situation where confounding is unlikely. Conclusions: We discuss how these methods could be implemented in future mediation studies as well as the limitations and future directions for these methods.

AB - Background: Causal inference continues to be a critical aspect of evaluation research. Recent research in causal inference for statistical mediation has focused on addressing the sequential ignorability assumption; specifically, that there is no confounding between the mediator and the outcome variable. Objectives: This article compares and contrasts three different methods for assessing sensitivity to confounding and describes the graphical depiction of these methods. Design: Two types of data were used to fully examine the plots for sensitivity analysis. The first type was generated data from a single mediator model with a confounder influencing both the mediator and the outcome variable. The second was data from an actual intervention study. With both types of data, situations are examined where confounding has a large effect and a small effect. Subjects: The nonsimulated data were from a large intervention study to decrease intentions to use steroids among high school football players. We demonstrate one situation where confounding is likely and another situation where confounding is unlikely. Conclusions: We discuss how these methods could be implemented in future mediation studies as well as the limitations and future directions for these methods.

KW - causal inference

KW - confounder bias

KW - indirect effects

KW - mediation

KW - sensitivity analysis

UR - http://www.scopus.com/inward/record.url?scp=84900296079&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900296079&partnerID=8YFLogxK

U2 - 10.1177/0193841X14524576

DO - 10.1177/0193841X14524576

M3 - Article

C2 - 24681690

AN - SCOPUS:84900296079

VL - 37

SP - 405

EP - 431

JO - Evaluation Review

JF - Evaluation Review

SN - 0193-841X

IS - 5

ER -