Assurance for clinical trial design with normally distributed outcomes: Eliciting uncertainty about variances.

Ziyad A Alhussain,Jeremy E Oakley

doi:10.1002/pst.2040

Ziyad A Alhussain, Jeremy E Oakley

Open Access

https://doi.org/10.1002/pst.2040

Copy DOI

Abstract

The assurance method is growing in popularity in clinical trial planning. The method involves eliciting a prior distribution for the treatment effect, and then calculating the probability that a proposed trial will produce a "successful" outcome. For normally distributed observations, uncertainty about the variance of the normal distribution also needs to be accounted for, but there is little guidance in the literature on how to elicit a distribution for a variance parameter. We present a simple elicitation method, and illustrate how the elicited distribution is incorporated within an assurance calculation. We also consider multi-stage trials, where a decision to proceed with a larger trial will follow from the outcome of a smaller trial; we illustrate the role of the elicited distribution in assessing the information provided by a proposed smaller trial. Free software is available for implementing our methods.

Highlights

Assurance is a Bayesian alternative to a power calculation for choosing a sample size in a clinical trial
They describe how the process of deriving an assurance supports their decision making, in particular, how the elicitation of a prior distribution provides a formal assessment of the evidence and uncertainties regarding a treatment effect
They give examples where modifications are made to trial designs when it is been judged necessary to mitigate against risks and uncertainties identified at the elicitation stage; using the assurance method can result in more than just a modified sample size assessment

Summary

Introduction

Assurance is a Bayesian alternative to a power calculation for choosing a sample size in a clinical trial. We consider the unconditional probability of the same event R, but with a different interpretation of δ: we interpret δ as the true treatment effect, elicit a prior distribution πÀδ, σ2t , σ Suppose we wish to elicit an expert's opinion about the variance parameter σ2 of a random variable X that follows a normal distribution with a known mean μ.

Results

Conclusion