Assessing the heterogeneity of treatment effects via potential outcomes of individual patients

Zhiwei Zhang, Chenguang Wang, Lei Nie, Guoxing Soon

Research output: Contribution to journalArticle

Abstract

Summary: There is growing interest in understanding the heterogeneity of treatment effects (HTE), which has important implications in treatment evaluation and selection. The standard approach to assessing HTE (i.e. subgroup analyses based on known effect modifiers) is informative about the heterogeneity between subpopulations but not within. It is arguably more informative to assess HTE in terms of individual treatment effects, which can be defined by using potential outcomes. However, estimation of HTE based on potential outcomes is challenged by the lack of complete identifiability. The paper proposes methods to deal with the identifiability problem by using relevant information in baseline covariates and repeated measurements. If a set of covariates is sufficient for explaining the dependence between potential outcomes, the joint distribution of potential outcomes and hence all measures of HTE will then be identified under a conditional independence assumption. Possible violations of this assumption can be addressed by including a random effect to account for residual dependence or by specifying the conditional dependence structure directly. The methods proposed are shown to reduce effectively the uncertainty about HTE in a trial of human immunodeficiency virus.

Original languageEnglish (US)
Pages (from-to)687-704
Number of pages18
JournalJournal of the Royal Statistical Society. Series C: Applied Statistics
Volume62
Issue number5
DOIs
StatePublished - Nov 2013

Fingerprint

Potential Outcomes
Treatment Effects
Identifiability
Covariates
Repeated Measurements
Conditional Independence
Dependence Structure
Treatment effects
Potential outcomes
Random Effects
Joint Distribution
Virus
Baseline
Subgroup
Sufficient
Uncertainty
Evaluation

Keywords

  • Causal inference
  • Conditional independence
  • Copula
  • Counterfactual
  • Random effect
  • Sensitivity analysis

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Assessing the heterogeneity of treatment effects via potential outcomes of individual patients. / Zhang, Zhiwei; Wang, Chenguang; Nie, Lei; Soon, Guoxing.

In: Journal of the Royal Statistical Society. Series C: Applied Statistics, Vol. 62, No. 5, 11.2013, p. 687-704.

Research output: Contribution to journalArticle

@article{78a2cc8a3c1a41cab2799c065fc2253e,
title = "Assessing the heterogeneity of treatment effects via potential outcomes of individual patients",
abstract = "Summary: There is growing interest in understanding the heterogeneity of treatment effects (HTE), which has important implications in treatment evaluation and selection. The standard approach to assessing HTE (i.e. subgroup analyses based on known effect modifiers) is informative about the heterogeneity between subpopulations but not within. It is arguably more informative to assess HTE in terms of individual treatment effects, which can be defined by using potential outcomes. However, estimation of HTE based on potential outcomes is challenged by the lack of complete identifiability. The paper proposes methods to deal with the identifiability problem by using relevant information in baseline covariates and repeated measurements. If a set of covariates is sufficient for explaining the dependence between potential outcomes, the joint distribution of potential outcomes and hence all measures of HTE will then be identified under a conditional independence assumption. Possible violations of this assumption can be addressed by including a random effect to account for residual dependence or by specifying the conditional dependence structure directly. The methods proposed are shown to reduce effectively the uncertainty about HTE in a trial of human immunodeficiency virus.",
keywords = "Causal inference, Conditional independence, Copula, Counterfactual, Random effect, Sensitivity analysis",
author = "Zhiwei Zhang and Chenguang Wang and Lei Nie and Guoxing Soon",
year = "2013",
month = "11",
doi = "10.1111/rssc.12012",
language = "English (US)",
volume = "62",
pages = "687--704",
journal = "Journal of the Royal Statistical Society. Series C: Applied Statistics",
issn = "0035-9254",
publisher = "Wiley-Blackwell",
number = "5",

}

TY - JOUR

T1 - Assessing the heterogeneity of treatment effects via potential outcomes of individual patients

AU - Zhang, Zhiwei

AU - Wang, Chenguang

AU - Nie, Lei

AU - Soon, Guoxing

PY - 2013/11

Y1 - 2013/11

N2 - Summary: There is growing interest in understanding the heterogeneity of treatment effects (HTE), which has important implications in treatment evaluation and selection. The standard approach to assessing HTE (i.e. subgroup analyses based on known effect modifiers) is informative about the heterogeneity between subpopulations but not within. It is arguably more informative to assess HTE in terms of individual treatment effects, which can be defined by using potential outcomes. However, estimation of HTE based on potential outcomes is challenged by the lack of complete identifiability. The paper proposes methods to deal with the identifiability problem by using relevant information in baseline covariates and repeated measurements. If a set of covariates is sufficient for explaining the dependence between potential outcomes, the joint distribution of potential outcomes and hence all measures of HTE will then be identified under a conditional independence assumption. Possible violations of this assumption can be addressed by including a random effect to account for residual dependence or by specifying the conditional dependence structure directly. The methods proposed are shown to reduce effectively the uncertainty about HTE in a trial of human immunodeficiency virus.

AB - Summary: There is growing interest in understanding the heterogeneity of treatment effects (HTE), which has important implications in treatment evaluation and selection. The standard approach to assessing HTE (i.e. subgroup analyses based on known effect modifiers) is informative about the heterogeneity between subpopulations but not within. It is arguably more informative to assess HTE in terms of individual treatment effects, which can be defined by using potential outcomes. However, estimation of HTE based on potential outcomes is challenged by the lack of complete identifiability. The paper proposes methods to deal with the identifiability problem by using relevant information in baseline covariates and repeated measurements. If a set of covariates is sufficient for explaining the dependence between potential outcomes, the joint distribution of potential outcomes and hence all measures of HTE will then be identified under a conditional independence assumption. Possible violations of this assumption can be addressed by including a random effect to account for residual dependence or by specifying the conditional dependence structure directly. The methods proposed are shown to reduce effectively the uncertainty about HTE in a trial of human immunodeficiency virus.

KW - Causal inference

KW - Conditional independence

KW - Copula

KW - Counterfactual

KW - Random effect

KW - Sensitivity analysis

UR - http://www.scopus.com/inward/record.url?scp=84885424877&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885424877&partnerID=8YFLogxK

U2 - 10.1111/rssc.12012

DO - 10.1111/rssc.12012

M3 - Article

C2 - 25506088

AN - SCOPUS:84885424877

VL - 62

SP - 687

EP - 704

JO - Journal of the Royal Statistical Society. Series C: Applied Statistics

JF - Journal of the Royal Statistical Society. Series C: Applied Statistics

SN - 0035-9254

IS - 5

ER -