Toggle Main Menu Toggle Search

Open Access padlockePrints

A response-adaptive randomization procedure for multi-armed clinical trials with normally distributed outcomes

Lookup NU author(s): Dr Faye Williamson



This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).


We propose a novel response‐adaptive randomization procedure for multi‐armed trials with continuous outcomes that are assumed to be normally distributed. Our proposed rule is non‐myopic, and oriented toward a patient benefit objective, yet maintains computational feasibility. We derive our response‐adaptive algorithm based on the Gittins index for the multi‐armed bandit problem, as a modification of the method first introduced in Villar et al. (Biometrics, 71, pp. 969‐978). The resulting procedure can be implemented under the assumption of both known or unknown variance. We illustrate the proposed procedure by simulations in the context of phase II cancer trials. Our results show that, in a multi‐armed setting, there are efficiency and patient benefit gains of using a response‐adaptive allocation procedure with a continuous endpoint instead of a binary one. These gains persist even if an anticipated low rate of missing data due to deaths, dropouts, or complete responses is imputed online through a procedure first introduced in this paper. Additionally, we discuss how there are response‐adaptive designs that outperform the traditional equal randomized design both in terms of efficiency and patient benefit measures in the multi‐armed trial context

Publication metadata

Author(s): Williamson SF, Villar SS

Publication type: Article

Publication status: Published

Journal: Biometrics

Year: 2019

Volume: 76

Issue: 1

Pages: 197-209

Print publication date: 11/03/2020

Online publication date: 19/07/2019

Acceptance date: 24/06/2019

Date deposited: 13/04/2021

ISSN (print): 0006-341X

ISSN (electronic): 1541-0420

Publisher: Wiley-Blackwell Publishing Ltd.


DOI: 10.1111/biom.13119


Altmetrics provided by Altmetric


Funder referenceFunder name
MC UU 00002/3