A Viable Alternative When Propensity Scores Fail: Evaluation of Inverse Propensity Weighting and Sequential G-Estimation in a Two-Wave Mediation Model

Matthew J. Valente, David P. MacKinnon, Gina L. Mazza

Research output: Contribution to journalArticle

Abstract

Two methods from the potential outcomes framework–inverse propensity weighting (IPW) and sequential G-estimation–were evaluated and compared to linear regression for estimating the mediated effect in a two-wave design with a randomized intervention and continuous mediator and outcome. Baseline measures of the mediator and outcome can be considered confounders of the follow-up mediator–outcome relation for which adjustment is necessary to eliminate bias. To adjust for baseline measures of the mediator and outcome, IPW uses stabilized inverse propensity weights whereas sequential G-estimation uses regression adjustment. Theoretical differences between the models are described, and Monte Carlo simulations compared the performance of linear regression; IPW without weight truncation; IPW with weights truncated at the 1st/99th, 5th/95th, and 10th/90th percentiles; and sequential G-estimation. Sequential G-estimation performed similarly to linear regression, but IPW provided a biased estimate of the mediated effect, lower power, lower confidence interval coverage, and higher mean squared error. Simulation results show that IPW failed to fully adjust the follow-up mediator–outcome relation for confounding due to the baseline measures. We then compared the mediated effect estimates using data from a randomized experiment evaluating a steroid prevention program for high school athletes. Implications and future directions are discussed.

Original languageEnglish (US)
JournalMultivariate Behavioral Research
DOIs
StatePublished - Jan 1 2019

Fingerprint

Propensity Score
Mediation
Weighting
Mediator
Linear Models
Linear regression
Weights and Measures
Baseline
Alternatives
Evaluation
Outcome Assessment (Health Care)
Adjustment
Randomized Experiments
Potential Outcomes
Athletes
Steroids
Confounding
Percentile
Mean Squared Error
Truncation

Keywords

  • Causal mediation
  • inverse propensity weighting
  • longitudinal mediation
  • potential outcomes framework
  • sequential G-estimation

ASJC Scopus subject areas

  • Statistics and Probability
  • Experimental and Cognitive Psychology
  • Arts and Humanities (miscellaneous)

Cite this

@article{f79d0714dce34abda58c64bd31f40d42,
title = "A Viable Alternative When Propensity Scores Fail: Evaluation of Inverse Propensity Weighting and Sequential G-Estimation in a Two-Wave Mediation Model",
abstract = "Two methods from the potential outcomes framework–inverse propensity weighting (IPW) and sequential G-estimation–were evaluated and compared to linear regression for estimating the mediated effect in a two-wave design with a randomized intervention and continuous mediator and outcome. Baseline measures of the mediator and outcome can be considered confounders of the follow-up mediator–outcome relation for which adjustment is necessary to eliminate bias. To adjust for baseline measures of the mediator and outcome, IPW uses stabilized inverse propensity weights whereas sequential G-estimation uses regression adjustment. Theoretical differences between the models are described, and Monte Carlo simulations compared the performance of linear regression; IPW without weight truncation; IPW with weights truncated at the 1st/99th, 5th/95th, and 10th/90th percentiles; and sequential G-estimation. Sequential G-estimation performed similarly to linear regression, but IPW provided a biased estimate of the mediated effect, lower power, lower confidence interval coverage, and higher mean squared error. Simulation results show that IPW failed to fully adjust the follow-up mediator–outcome relation for confounding due to the baseline measures. We then compared the mediated effect estimates using data from a randomized experiment evaluating a steroid prevention program for high school athletes. Implications and future directions are discussed.",
keywords = "Causal mediation, inverse propensity weighting, longitudinal mediation, potential outcomes framework, sequential G-estimation",
author = "Valente, {Matthew J.} and MacKinnon, {David P.} and Mazza, {Gina L.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1080/00273171.2019.1614429",
language = "English (US)",
journal = "Multivariate Behavioral Research",
issn = "0027-3171",
publisher = "Psychology Press Ltd",

}

TY - JOUR

T1 - A Viable Alternative When Propensity Scores Fail

T2 - Evaluation of Inverse Propensity Weighting and Sequential G-Estimation in a Two-Wave Mediation Model

AU - Valente, Matthew J.

AU - MacKinnon, David P.

AU - Mazza, Gina L.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Two methods from the potential outcomes framework–inverse propensity weighting (IPW) and sequential G-estimation–were evaluated and compared to linear regression for estimating the mediated effect in a two-wave design with a randomized intervention and continuous mediator and outcome. Baseline measures of the mediator and outcome can be considered confounders of the follow-up mediator–outcome relation for which adjustment is necessary to eliminate bias. To adjust for baseline measures of the mediator and outcome, IPW uses stabilized inverse propensity weights whereas sequential G-estimation uses regression adjustment. Theoretical differences between the models are described, and Monte Carlo simulations compared the performance of linear regression; IPW without weight truncation; IPW with weights truncated at the 1st/99th, 5th/95th, and 10th/90th percentiles; and sequential G-estimation. Sequential G-estimation performed similarly to linear regression, but IPW provided a biased estimate of the mediated effect, lower power, lower confidence interval coverage, and higher mean squared error. Simulation results show that IPW failed to fully adjust the follow-up mediator–outcome relation for confounding due to the baseline measures. We then compared the mediated effect estimates using data from a randomized experiment evaluating a steroid prevention program for high school athletes. Implications and future directions are discussed.

AB - Two methods from the potential outcomes framework–inverse propensity weighting (IPW) and sequential G-estimation–were evaluated and compared to linear regression for estimating the mediated effect in a two-wave design with a randomized intervention and continuous mediator and outcome. Baseline measures of the mediator and outcome can be considered confounders of the follow-up mediator–outcome relation for which adjustment is necessary to eliminate bias. To adjust for baseline measures of the mediator and outcome, IPW uses stabilized inverse propensity weights whereas sequential G-estimation uses regression adjustment. Theoretical differences between the models are described, and Monte Carlo simulations compared the performance of linear regression; IPW without weight truncation; IPW with weights truncated at the 1st/99th, 5th/95th, and 10th/90th percentiles; and sequential G-estimation. Sequential G-estimation performed similarly to linear regression, but IPW provided a biased estimate of the mediated effect, lower power, lower confidence interval coverage, and higher mean squared error. Simulation results show that IPW failed to fully adjust the follow-up mediator–outcome relation for confounding due to the baseline measures. We then compared the mediated effect estimates using data from a randomized experiment evaluating a steroid prevention program for high school athletes. Implications and future directions are discussed.

KW - Causal mediation

KW - inverse propensity weighting

KW - longitudinal mediation

KW - potential outcomes framework

KW - sequential G-estimation

UR - http://www.scopus.com/inward/record.url?scp=85067900888&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067900888&partnerID=8YFLogxK

U2 - 10.1080/00273171.2019.1614429

DO - 10.1080/00273171.2019.1614429

M3 - Article

AN - SCOPUS:85067900888

JO - Multivariate Behavioral Research

JF - Multivariate Behavioral Research

SN - 0027-3171

ER -