Designed extension of survival studies

Application to clinical trials with unrecognized heterogeneity

Yi Li, Mei Chiung Shih, Rebecca Betensky

Research output: Contribution to journalArticle

Abstract

It is well known that unrecognized heterogeneity among patients, such as is conferred by genetic subtype, can undermine the power of a randomized trial, designed under the assumption of homogeneity, to detect a truly beneficial treatment. We consider the conditional power approach to allow for recovery of power under unexplained heterogeneity. While Proschan and Hunsberger (1995) confined the application of conditional power design to normally distributed observations, we consider more general and difficult settings in which the data are in the framework of continuous time and are subject to censoring. In particular, we derive a procedure appropriate for the analysis of the weighted log rank test under the assumption of a proportional hazards frailty model. The proposed method is illustrated through application to a brain tumor trial.

Original languageEnglish (US)
Pages (from-to)1567-1589
Number of pages23
JournalStatistica Sinica
Volume17
Issue number4
StatePublished - Oct 1 2007

Fingerprint

Conditional Power
Clinical Trials
Log-rank Test
Brain Tumor
Frailty Model
Hazard Models
Randomized Trial
Proportional Hazards
Censoring
Homogeneity
Continuous Time
Recovery
Clinical trials

Keywords

  • Adaptive design
  • Conditional power
  • Frailty model

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Designed extension of survival studies : Application to clinical trials with unrecognized heterogeneity. / Li, Yi; Shih, Mei Chiung; Betensky, Rebecca.

In: Statistica Sinica, Vol. 17, No. 4, 01.10.2007, p. 1567-1589.

Research output: Contribution to journalArticle

Li, Yi ; Shih, Mei Chiung ; Betensky, Rebecca. / Designed extension of survival studies : Application to clinical trials with unrecognized heterogeneity. In: Statistica Sinica. 2007 ; Vol. 17, No. 4. pp. 1567-1589.
@article{347d3b58a11e4863a9d6bbd2abfc9f73,
title = "Designed extension of survival studies: Application to clinical trials with unrecognized heterogeneity",
abstract = "It is well known that unrecognized heterogeneity among patients, such as is conferred by genetic subtype, can undermine the power of a randomized trial, designed under the assumption of homogeneity, to detect a truly beneficial treatment. We consider the conditional power approach to allow for recovery of power under unexplained heterogeneity. While Proschan and Hunsberger (1995) confined the application of conditional power design to normally distributed observations, we consider more general and difficult settings in which the data are in the framework of continuous time and are subject to censoring. In particular, we derive a procedure appropriate for the analysis of the weighted log rank test under the assumption of a proportional hazards frailty model. The proposed method is illustrated through application to a brain tumor trial.",
keywords = "Adaptive design, Conditional power, Frailty model",
author = "Yi Li and Shih, {Mei Chiung} and Rebecca Betensky",
year = "2007",
month = "10",
day = "1",
language = "English (US)",
volume = "17",
pages = "1567--1589",
journal = "Statistica Sinica",
issn = "1017-0405",
publisher = "Institute of Statistical Science",
number = "4",

}

TY - JOUR

T1 - Designed extension of survival studies

T2 - Application to clinical trials with unrecognized heterogeneity

AU - Li, Yi

AU - Shih, Mei Chiung

AU - Betensky, Rebecca

PY - 2007/10/1

Y1 - 2007/10/1

N2 - It is well known that unrecognized heterogeneity among patients, such as is conferred by genetic subtype, can undermine the power of a randomized trial, designed under the assumption of homogeneity, to detect a truly beneficial treatment. We consider the conditional power approach to allow for recovery of power under unexplained heterogeneity. While Proschan and Hunsberger (1995) confined the application of conditional power design to normally distributed observations, we consider more general and difficult settings in which the data are in the framework of continuous time and are subject to censoring. In particular, we derive a procedure appropriate for the analysis of the weighted log rank test under the assumption of a proportional hazards frailty model. The proposed method is illustrated through application to a brain tumor trial.

AB - It is well known that unrecognized heterogeneity among patients, such as is conferred by genetic subtype, can undermine the power of a randomized trial, designed under the assumption of homogeneity, to detect a truly beneficial treatment. We consider the conditional power approach to allow for recovery of power under unexplained heterogeneity. While Proschan and Hunsberger (1995) confined the application of conditional power design to normally distributed observations, we consider more general and difficult settings in which the data are in the framework of continuous time and are subject to censoring. In particular, we derive a procedure appropriate for the analysis of the weighted log rank test under the assumption of a proportional hazards frailty model. The proposed method is illustrated through application to a brain tumor trial.

KW - Adaptive design

KW - Conditional power

KW - Frailty model

UR - http://www.scopus.com/inward/record.url?scp=38549147058&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38549147058&partnerID=8YFLogxK

M3 - Article

VL - 17

SP - 1567

EP - 1589

JO - Statistica Sinica

JF - Statistica Sinica

SN - 1017-0405

IS - 4

ER -