Group sequential designs with prospectively planned rules for subpopulation enrichment

Research output: Contribution to journalArticle

Abstract

We propose a class of randomized trial designs aimed at gaining the advantages of wider generalizability and faster recruitment while mitigating the risks of including a population for which there is greater a priori uncertainty. We focus on testing null hypotheses for the overall population and a predefined subpopulation. Our designs have preplanned rules for modifying enrollment criteria based on data accrued at interim analyses. For example, enrollment can be restricted if the participants from a predefined subpopulation are not benefiting from the new treatment. Our designs have the following features: the multiple testing procedure fully leverages the correlation among statistics for different populations; the asymptotic familywise Type I error rate is strongly controlled; for outcomes that are binary or normally distributed, the decision rule and multiple testing procedure are functions of the data only through minimal sufficient statistics. Our designs incorporate standard group sequential boundaries for each population of interest; this may be helpful in communicating the designs, because many clinical investigators are familiar with such boundaries, which can be summarized succinctly in a single table or graph. We demonstrate these designs through simulations of a Phase III trial of a new treatment for stroke. User-friendly, free software implementing these designs is described.

Original languageEnglish (US)
Pages (from-to)3776-3791
Number of pages16
JournalStatistics in Medicine
Volume35
Issue number21
DOIs
StatePublished - Sep 20 2016

Fingerprint

Group Sequential Design
Population
Software Design
Population Characteristics
Multiple Testing
Uncertainty
Stroke
Research Personnel
Group Sequential
Randomized Trial
Sufficient Statistics
Type I Error Rate
Decision Rules
Design
Null hypothesis
Leverage
Table
Binary
Statistics
Testing

Keywords

  • adaptive enrichment design
  • group sequential design
  • optimal sample size

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability
  • Medicine(all)

Cite this

Group sequential designs with prospectively planned rules for subpopulation enrichment. / Rosenblum, Michael Aaron; Luber, Brandon; Thompson, Richard; Hanley, Daniel F.

In: Statistics in Medicine, Vol. 35, No. 21, 20.09.2016, p. 3776-3791.

Research output: Contribution to journalArticle

@article{6998603c8e0c4a498d4adbf7a4d261cd,
title = "Group sequential designs with prospectively planned rules for subpopulation enrichment",
abstract = "We propose a class of randomized trial designs aimed at gaining the advantages of wider generalizability and faster recruitment while mitigating the risks of including a population for which there is greater a priori uncertainty. We focus on testing null hypotheses for the overall population and a predefined subpopulation. Our designs have preplanned rules for modifying enrollment criteria based on data accrued at interim analyses. For example, enrollment can be restricted if the participants from a predefined subpopulation are not benefiting from the new treatment. Our designs have the following features: the multiple testing procedure fully leverages the correlation among statistics for different populations; the asymptotic familywise Type I error rate is strongly controlled; for outcomes that are binary or normally distributed, the decision rule and multiple testing procedure are functions of the data only through minimal sufficient statistics. Our designs incorporate standard group sequential boundaries for each population of interest; this may be helpful in communicating the designs, because many clinical investigators are familiar with such boundaries, which can be summarized succinctly in a single table or graph. We demonstrate these designs through simulations of a Phase III trial of a new treatment for stroke. User-friendly, free software implementing these designs is described.",
keywords = "adaptive enrichment design, group sequential design, optimal sample size",
author = "Rosenblum, {Michael Aaron} and Brandon Luber and Richard Thompson and Hanley, {Daniel F}",
year = "2016",
month = "9",
day = "20",
doi = "10.1002/sim.6957",
language = "English (US)",
volume = "35",
pages = "3776--3791",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "21",

}

TY - JOUR

T1 - Group sequential designs with prospectively planned rules for subpopulation enrichment

AU - Rosenblum, Michael Aaron

AU - Luber, Brandon

AU - Thompson, Richard

AU - Hanley, Daniel F

PY - 2016/9/20

Y1 - 2016/9/20

N2 - We propose a class of randomized trial designs aimed at gaining the advantages of wider generalizability and faster recruitment while mitigating the risks of including a population for which there is greater a priori uncertainty. We focus on testing null hypotheses for the overall population and a predefined subpopulation. Our designs have preplanned rules for modifying enrollment criteria based on data accrued at interim analyses. For example, enrollment can be restricted if the participants from a predefined subpopulation are not benefiting from the new treatment. Our designs have the following features: the multiple testing procedure fully leverages the correlation among statistics for different populations; the asymptotic familywise Type I error rate is strongly controlled; for outcomes that are binary or normally distributed, the decision rule and multiple testing procedure are functions of the data only through minimal sufficient statistics. Our designs incorporate standard group sequential boundaries for each population of interest; this may be helpful in communicating the designs, because many clinical investigators are familiar with such boundaries, which can be summarized succinctly in a single table or graph. We demonstrate these designs through simulations of a Phase III trial of a new treatment for stroke. User-friendly, free software implementing these designs is described.

AB - We propose a class of randomized trial designs aimed at gaining the advantages of wider generalizability and faster recruitment while mitigating the risks of including a population for which there is greater a priori uncertainty. We focus on testing null hypotheses for the overall population and a predefined subpopulation. Our designs have preplanned rules for modifying enrollment criteria based on data accrued at interim analyses. For example, enrollment can be restricted if the participants from a predefined subpopulation are not benefiting from the new treatment. Our designs have the following features: the multiple testing procedure fully leverages the correlation among statistics for different populations; the asymptotic familywise Type I error rate is strongly controlled; for outcomes that are binary or normally distributed, the decision rule and multiple testing procedure are functions of the data only through minimal sufficient statistics. Our designs incorporate standard group sequential boundaries for each population of interest; this may be helpful in communicating the designs, because many clinical investigators are familiar with such boundaries, which can be summarized succinctly in a single table or graph. We demonstrate these designs through simulations of a Phase III trial of a new treatment for stroke. User-friendly, free software implementing these designs is described.

KW - adaptive enrichment design

KW - group sequential design

KW - optimal sample size

UR - http://www.scopus.com/inward/record.url?scp=84980378927&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84980378927&partnerID=8YFLogxK

U2 - 10.1002/sim.6957

DO - 10.1002/sim.6957

M3 - Article

C2 - 27076411

AN - SCOPUS:84980378927

VL - 35

SP - 3776

EP - 3791

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 21

ER -