Approaches to treatment effect heterogeneity in the presence of confounding

Sarah C. Anoke, Sharon Lise Normand, Corwin Zigler

Research output: Contribution to journalArticle

Abstract

The literature on causal effect estimation tends to focus on the population mean estimand, which is less informative as medical treatments are becoming more personalized and there is increasing awareness that subpopulations of individuals may experience a group-specific effect that differs from the population average. In fact, it is possible that there is underlying systematic effect heterogeneity that is obscured by focusing on the population mean estimand. In this context, understanding which covariates contribute to this treatment effect heterogeneity (TEH) and how these covariates determine the differential treatment effect (TE) is an important consideration. Towards such an understanding, this paper briefly reviews three approaches used in making causal inferences and conducts a simulation study to compare these approaches according to their performance in an exploratory evaluation of TEH when the heterogeneous subgroups are not known a priori. Performance metrics include the detection of any heterogeneity, the identification and characterization of heterogeneous subgroups, and unconfounded estimation of the TE within subgroups. The methods are then deployed in a comparative effectiveness evaluation of drug-eluting versus bare-metal stents among 54 099 Medicare beneficiaries in the continental United States admitted to a hospital with acute myocardial infarction in 2008.

Original languageEnglish (US)
Pages (from-to)2797-2815
Number of pages19
JournalStatistics in Medicine
Volume38
Issue number15
DOIs
StatePublished - Jul 10 2019

Fingerprint

Confounding
Treatment Effects
Subgroup
Population
Covariates
Drug Evaluation
Effectiveness Evaluation
Medicare
Stent
Causal Inference
Acute Myocardial Infarction
Causal Effect
Stents
Performance Metrics
Metals
Myocardial Infarction
Drugs
Simulation Study
Tend
Evaluation

Keywords

  • causal inference
  • confounding
  • effect modification
  • observational data
  • subgroup estimation
  • treatment effect heterogeneity

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Approaches to treatment effect heterogeneity in the presence of confounding. / Anoke, Sarah C.; Normand, Sharon Lise; Zigler, Corwin.

In: Statistics in Medicine, Vol. 38, No. 15, 10.07.2019, p. 2797-2815.

Research output: Contribution to journalArticle

Anoke, Sarah C. ; Normand, Sharon Lise ; Zigler, Corwin. / Approaches to treatment effect heterogeneity in the presence of confounding. In: Statistics in Medicine. 2019 ; Vol. 38, No. 15. pp. 2797-2815.
@article{817a2a3bc85848cfa67f297c81aac5dc,
title = "Approaches to treatment effect heterogeneity in the presence of confounding",
abstract = "The literature on causal effect estimation tends to focus on the population mean estimand, which is less informative as medical treatments are becoming more personalized and there is increasing awareness that subpopulations of individuals may experience a group-specific effect that differs from the population average. In fact, it is possible that there is underlying systematic effect heterogeneity that is obscured by focusing on the population mean estimand. In this context, understanding which covariates contribute to this treatment effect heterogeneity (TEH) and how these covariates determine the differential treatment effect (TE) is an important consideration. Towards such an understanding, this paper briefly reviews three approaches used in making causal inferences and conducts a simulation study to compare these approaches according to their performance in an exploratory evaluation of TEH when the heterogeneous subgroups are not known a priori. Performance metrics include the detection of any heterogeneity, the identification and characterization of heterogeneous subgroups, and unconfounded estimation of the TE within subgroups. The methods are then deployed in a comparative effectiveness evaluation of drug-eluting versus bare-metal stents among 54 099 Medicare beneficiaries in the continental United States admitted to a hospital with acute myocardial infarction in 2008.",
keywords = "causal inference, confounding, effect modification, observational data, subgroup estimation, treatment effect heterogeneity",
author = "Anoke, {Sarah C.} and Normand, {Sharon Lise} and Corwin Zigler",
year = "2019",
month = "7",
day = "10",
doi = "10.1002/sim.8143",
language = "English (US)",
volume = "38",
pages = "2797--2815",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "15",

}

TY - JOUR

T1 - Approaches to treatment effect heterogeneity in the presence of confounding

AU - Anoke, Sarah C.

AU - Normand, Sharon Lise

AU - Zigler, Corwin

PY - 2019/7/10

Y1 - 2019/7/10

N2 - The literature on causal effect estimation tends to focus on the population mean estimand, which is less informative as medical treatments are becoming more personalized and there is increasing awareness that subpopulations of individuals may experience a group-specific effect that differs from the population average. In fact, it is possible that there is underlying systematic effect heterogeneity that is obscured by focusing on the population mean estimand. In this context, understanding which covariates contribute to this treatment effect heterogeneity (TEH) and how these covariates determine the differential treatment effect (TE) is an important consideration. Towards such an understanding, this paper briefly reviews three approaches used in making causal inferences and conducts a simulation study to compare these approaches according to their performance in an exploratory evaluation of TEH when the heterogeneous subgroups are not known a priori. Performance metrics include the detection of any heterogeneity, the identification and characterization of heterogeneous subgroups, and unconfounded estimation of the TE within subgroups. The methods are then deployed in a comparative effectiveness evaluation of drug-eluting versus bare-metal stents among 54 099 Medicare beneficiaries in the continental United States admitted to a hospital with acute myocardial infarction in 2008.

AB - The literature on causal effect estimation tends to focus on the population mean estimand, which is less informative as medical treatments are becoming more personalized and there is increasing awareness that subpopulations of individuals may experience a group-specific effect that differs from the population average. In fact, it is possible that there is underlying systematic effect heterogeneity that is obscured by focusing on the population mean estimand. In this context, understanding which covariates contribute to this treatment effect heterogeneity (TEH) and how these covariates determine the differential treatment effect (TE) is an important consideration. Towards such an understanding, this paper briefly reviews three approaches used in making causal inferences and conducts a simulation study to compare these approaches according to their performance in an exploratory evaluation of TEH when the heterogeneous subgroups are not known a priori. Performance metrics include the detection of any heterogeneity, the identification and characterization of heterogeneous subgroups, and unconfounded estimation of the TE within subgroups. The methods are then deployed in a comparative effectiveness evaluation of drug-eluting versus bare-metal stents among 54 099 Medicare beneficiaries in the continental United States admitted to a hospital with acute myocardial infarction in 2008.

KW - causal inference

KW - confounding

KW - effect modification

KW - observational data

KW - subgroup estimation

KW - treatment effect heterogeneity

UR - http://www.scopus.com/inward/record.url?scp=85063636587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063636587&partnerID=8YFLogxK

U2 - 10.1002/sim.8143

DO - 10.1002/sim.8143

M3 - Article

C2 - 30931547

AN - SCOPUS:85063636587

VL - 38

SP - 2797

EP - 2815

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 15

ER -