BAYESIAN PREDICTIVE PERFORMANCE FOR EXPERIMENTAL DESIGN.

Merabet, H; Labdaoui, A

Sciences & technologie. A, sciences exactes
Volume 0, Numéro 37, Pages 31-35
2013-06-30

Bayesian Predictive Performance For Experimental Design.

Abstract

The aim of an exploratory clinical trial is to determine whether a new intervention is promising for further testing in confirmatory clinical trials. Most exploratory clinical trials are designed as single-arm trials using a binary outcome with or without interim monitoring for early stopping. In this paper, we are particularly interested in using the predictive Bayesian approach in clinical trials or objectives is the development of important evidence of an effect of interest we offer the procedure based on the notion satisfaction Index is based on the value of p and we are first given the data available to calculate a forecast of future satisfaction data as Bayesian predictive expect this index conditional on past observations. To illustrate the proposed procedure, we proposed the binomial model.