Frequentist performance of Bayesian inference with response-adaptive designs.
Summary of "Frequentist performance of Bayesian inference with response-adaptive designs."
In controlled clinical trials, where minimizing treatment failures is crucial, response-adaptive designs are attractive competitors to 1:1 randomized designs for comparing the success rates ϕ(1) and ϕ(2) of two treatments. In these designs each new treatment assignment depends on previous outcomes through some predefined rule. Here Play-The-Winner (PW), Randomized Play-The-Winner (RPW), Drop-The-Loser, Generalized Drop-the-Loser and Doubly adaptive Biased Coin Designs are considered for new treatment assignments. As frequentist inference relies on complex sampling distributions in those designs, we investigate how Bayesian inference, based on two independent Beta prior distributions, performs from a frequentist point-of-view. Performance is assessed through coverage probabilities of interval estimation procedures, power and minimization of failure count. It is shown that Bayesian inference can be favorably compared to frequentist procedures where the latter are available. The power of response-adaptive designs is generally very close to the power of 1:1 randomized design. However, failure count savings are generally small, except for the PW and Doubly adaptive Biased Coin designs in particular ranges of the true success rates. The RPW assignment rule has the worst performance, while PW, Generalized Drop-the-Loser or Doubly adaptive Biased Coin Designs may outperform other designs depending on different particular ranges of the true success rates. Copyright © 2010 John Wiley & Sons, Ltd.
Affiliation
ERIS, Laboratoire de Mathématique Raphaël Salem, CNRS and Université de Rouen, Avenue de l'Université, BP 12, 76801 Saint-Etienne-du-Rouvray, France. bruno.lecoutre@univ-rouen.fr.
Journal Details
This article was published in the following journal.
Name: Statistics in medicine
ISSN: 1097-0258
Pages: 3219-31
Links
- PubMed Source: http://www.ncbi.nlm.nih.gov/pubmed/21170916
- DOI: http://dx.doi.org/10.1002/sim.4025
Medical and Biotech [MESH] Definitions
Practice (psychology)
Performance of an act one or more times, with a view to its fixation or improvement; any performance of an act or behavior that leads to learning.
Feedback, Psychological
A mechanism of information stimulus and response that may control subsequent behavior, cognition, perception, or performance. (From APA Thesaurus of Psychological Index Terms, 8th ed.)
Athletic Performance
Carrying out of specific physical routines or procedures by one who is trained or skilled in physical activity. Performance is influenced by a combination of physiological, psychological, and socio-cultural factors.
Architectural Accessibility
Designs for approaching areas inside or outside facilities.
Logic
The science that investigates the principles governing correct or reliable inference and deals with the canons and criteria of validity in thought and demonstration. This system of reasoning is applicable to any branch of knowledge or study. (Random House Unabridged Dictionary, 2d ed & Sippl, Computer Dictionary, 4th ed)
PubMed Articles
Bayesian and frequentist models: legitimate choices for different purposes of clinical research.
Objective Bayesian and frequentist approaches to statistical modelling in epidemiology are often pitted against each other as if they represented diametrically opposing philosophies. However, both...
Increasingly complex applications involve large datasets in combination with nonlinear and high-dimensional mathematical models. In this context, statistical inference is a challenging issue that call...
Bayesian adaptive clinical trials: a dream for statisticians only?
Adaptive or 'flexible' designs have emerged, mostly within frequentist frameworks, as an effective way to speed up the therapeutic evaluation process. Because of their flexibility, Bayesian methods ha...
ABC-SysBio--approximate Bayesian computation in Python with GPU support.
MOTIVATION: The growing field of systems biology has driven demand for flexible tools to model and simulate biological systems. Two established problems in the modeling of biological processes are mod...
A Bayesian subgroup analysis with a zero-enriched Polya Urn scheme.
We introduce a new approach to inference for subgroups in clinical trials. We use Bayesian model selection, and a threshold on posterior model probabilities to identify subgroup effects for reporting....
Clinical Trials
The purpose of this study is to compare the performance of 4 designs of the DePuy Ultima LX hip stem in the treatment of patients with hip joint disease requiring a total hip replacement....
Closed Loop Stimulation, Cognitive Performance, and Quality of Life in Pacemaker Patients
The purpose of this study is to compare the influence of accelerometer-based rate adaptation and Closed Loop Stimulation on cognitive performance and quality of life in pacemaker patients.
Adaptive Cardiac Resynchronization Therapy Study
The purpose of this study is to show that Adaptive CRT is at least as good at optimizing a patient's cardiac resynchronization therapy (CRT) as the current method of using an echocardiogra...
Adaptive Behaviors Among Women With Bowel Incontinence: The ABBI Trial
This study focuses on the validation of the Adaptation Index instrument as a measurement of adaptive behaviors used to reduce symptoms of FI and to describe the use of adaptive behaviors a...
The primary objective is to compare the gum response to three different dental implant designs when placed in the front region of the upper jaw. The changes from baseline to one year after...
