Inverse probability weighting for covariate adjustment in randomized studies

Changyu Shen, Xiaochun Li, Lingling Li

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Covariate adjustment in randomized clinical trials has the potential benefit of precision gain. It also has the potential pitfall of reduced objectivity as it opens the possibility of selecting a 'favorable' model that yields strong treatment benefit estimate. Although there is a large volume of statistical literature targeting on the first aspect, realistic solutions to enforce objective inference and improve precision are rare. As a typical randomized trial needs to accommodate many implementation issues beyond statistical considerations, maintaining the objectivity is at least as important as precision gain if not more, particularly from the perspective of the regulatory agencies. In this article, we propose a two-stage estimation procedure based on inverse probability weighting to achieve better precision without compromising objectivity. The procedure is designed in a way such that the covariate adjustment is performed before seeing the outcome, effectively reducing the possibility of selecting a 'favorable' model that yields a strong intervention effect. Both theoretical and numerical properties of the estimation procedure are presented. Application of the proposed method to a real data example is presented.

Original languageEnglish
Pages (from-to)555-568
Number of pages14
JournalStatistics in Medicine
Volume33
Issue number4
DOIs
StatePublished - Feb 20 2014

Fingerprint

Inverse Probability Weighting
Covariates
Adjustment
Two-stage Estimation
Randomized Clinical Trial
Randomized Trial
Randomized Controlled Trials
Model
Estimate

Keywords

  • Clinical trials
  • Covariate adjustment
  • Efficiency
  • Inverse probability weighting
  • Objectivity

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Inverse probability weighting for covariate adjustment in randomized studies. / Shen, Changyu; Li, Xiaochun; Li, Lingling.

In: Statistics in Medicine, Vol. 33, No. 4, 20.02.2014, p. 555-568.

Research output: Contribution to journalArticle

@article{9ccaec2a62f44493a42716fdd63a18a4,
title = "Inverse probability weighting for covariate adjustment in randomized studies",
abstract = "Covariate adjustment in randomized clinical trials has the potential benefit of precision gain. It also has the potential pitfall of reduced objectivity as it opens the possibility of selecting a 'favorable' model that yields strong treatment benefit estimate. Although there is a large volume of statistical literature targeting on the first aspect, realistic solutions to enforce objective inference and improve precision are rare. As a typical randomized trial needs to accommodate many implementation issues beyond statistical considerations, maintaining the objectivity is at least as important as precision gain if not more, particularly from the perspective of the regulatory agencies. In this article, we propose a two-stage estimation procedure based on inverse probability weighting to achieve better precision without compromising objectivity. The procedure is designed in a way such that the covariate adjustment is performed before seeing the outcome, effectively reducing the possibility of selecting a 'favorable' model that yields a strong intervention effect. Both theoretical and numerical properties of the estimation procedure are presented. Application of the proposed method to a real data example is presented.",
keywords = "Clinical trials, Covariate adjustment, Efficiency, Inverse probability weighting, Objectivity",
author = "Changyu Shen and Xiaochun Li and Lingling Li",
year = "2014",
month = "2",
day = "20",
doi = "10.1002/sim.5969",
language = "English",
volume = "33",
pages = "555--568",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "4",

}

TY - JOUR

T1 - Inverse probability weighting for covariate adjustment in randomized studies

AU - Shen, Changyu

AU - Li, Xiaochun

AU - Li, Lingling

PY - 2014/2/20

Y1 - 2014/2/20

N2 - Covariate adjustment in randomized clinical trials has the potential benefit of precision gain. It also has the potential pitfall of reduced objectivity as it opens the possibility of selecting a 'favorable' model that yields strong treatment benefit estimate. Although there is a large volume of statistical literature targeting on the first aspect, realistic solutions to enforce objective inference and improve precision are rare. As a typical randomized trial needs to accommodate many implementation issues beyond statistical considerations, maintaining the objectivity is at least as important as precision gain if not more, particularly from the perspective of the regulatory agencies. In this article, we propose a two-stage estimation procedure based on inverse probability weighting to achieve better precision without compromising objectivity. The procedure is designed in a way such that the covariate adjustment is performed before seeing the outcome, effectively reducing the possibility of selecting a 'favorable' model that yields a strong intervention effect. Both theoretical and numerical properties of the estimation procedure are presented. Application of the proposed method to a real data example is presented.

AB - Covariate adjustment in randomized clinical trials has the potential benefit of precision gain. It also has the potential pitfall of reduced objectivity as it opens the possibility of selecting a 'favorable' model that yields strong treatment benefit estimate. Although there is a large volume of statistical literature targeting on the first aspect, realistic solutions to enforce objective inference and improve precision are rare. As a typical randomized trial needs to accommodate many implementation issues beyond statistical considerations, maintaining the objectivity is at least as important as precision gain if not more, particularly from the perspective of the regulatory agencies. In this article, we propose a two-stage estimation procedure based on inverse probability weighting to achieve better precision without compromising objectivity. The procedure is designed in a way such that the covariate adjustment is performed before seeing the outcome, effectively reducing the possibility of selecting a 'favorable' model that yields a strong intervention effect. Both theoretical and numerical properties of the estimation procedure are presented. Application of the proposed method to a real data example is presented.

KW - Clinical trials

KW - Covariate adjustment

KW - Efficiency

KW - Inverse probability weighting

KW - Objectivity

UR - http://www.scopus.com/inward/record.url?scp=84892478722&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84892478722&partnerID=8YFLogxK

U2 - 10.1002/sim.5969

DO - 10.1002/sim.5969

M3 - Article

C2 - 24038458

AN - SCOPUS:84892478722

VL - 33

SP - 555

EP - 568

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 4

ER -