Accessibility navigation

Choosing the number of doses and the cohort size for phase I dose-escalation studies

Zhou, Y. (2005) Choosing the number of doses and the cohort size for phase I dose-escalation studies. Drug Information Journal, 39 (2). pp. 125-138. ISSN 0092-8615

Full text not archived in this repository.

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.


This paper reviews Bayesian procedures for phase 1 dose-escalation studies and compares different dose schedules and cohort sizes. The methodology described is motivated by the situation of phase 1 dose-escalation studiesin oncology, that is, a single dose administered to each patient, with a single binary response ("toxicity"' or "no toxicity") observed. It is likely that a wider range of applications of the methodology is possible. In this paper, results from 10000-fold simulation runs conducted using the software package Bayesian ADEPT are presented. Four designs were compared under six scenarios. The simulation results indicate that there are slight advantages of having more dose levels and smaller cohort sizes.

Item Type:Article
Divisions:Science > School of Mathematical, Physical and Computational Sciences > Department of Mathematics and Statistics > Applied Statistics
ID Code:9429
Uncontrolled Keywords:Bayesian statistics , Computer software , Decision procedure , Dose-escalation , Phase I study

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation