Sequential allocation in clinical trials
- 1 January 1991
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 20 (3) , 791-805
- https://doi.org/10.1080/03610929108830531
Abstract
Suppose two treatments with binary responses are available for patients with some disease and that each patient will receive one of the two treatments. In this paper we consider the interests of patients both within and outside a trial using a Bayesian bandit approach and conclude that equal allocation is not appropriate for either group of patients. It is suggested that Gittins indices should be used ( using an approach called dynamic discounting by choosing the discount rate based on the number of future patients in the trial) if the disease is rare, and the least failures rule if the disease is common. Some analytical and simulation results are provided.Keywords
This publication has 18 references indexed in Scilit:
- [Investigating Therapies of Potentially Great Benefit: ECMO]: Comment: Recent Progress in Clinical Trial Designs that Adapt for Ethical PurposesStatistical Science, 1989
- Two-Stage BanditsThe Annals of Statistics, 1988
- Bayesian minimum sample size designs for the bernoulli selection problemSequential Analysis, 1988
- The Search for Optimality in Clinical TrialsInternational Statistical Review, 1985
- On the Allocation of Treatments in Sequential Medical TrialsInternational Statistical Review, 1985
- Multi-Armed Bandits with Discount Factor Near One: The Bernoulli CaseThe Annals of Statistics, 1981
- The two-armed banditBiometrika, 1975
- Finite Horizon Behavior of Policies for Two-Arm BanditsJournal of the American Statistical Association, 1974
- A Model for Selecting One of Two Medical TreatmentsJournal of the American Statistical Association, 1963
- Sequential Medical TrialsJournal of the American Statistical Association, 1963