Blinded sample size re-estimation in three-arm trials with 'gold standard' design

TL;DR

This paper evaluates blinded sample size re-estimation methods in three-arm 'gold standard' clinical trials with normally distributed outcomes, proposing an inflation factor to improve power accuracy.

Contribution

It compares various variance estimators for sample size re-estimation and introduces an inflation factor for the Xing-Ganju estimator to achieve proper trial power.

Findings

One-sample variance estimator leads to overpowered trials.

Unbiased estimators like Xing-Ganju cause underpowered trials without adjustment.

The proposed inflation factor balances power and maintains trial integrity.

Abstract

The sample size of a clinical trial relies on information about nuisance parameters such as the outcome variance. When no or only limited information is available, it has been proposed to include an internal pilot study in the design of the trial. Based on the results of the internal pilot study, the initially planned sample size can be adjusted. In this paper, we study blinded sample size re-estimation in the 'gold standard' design for normally distributed outcomes. The 'gold standard' design is a three-arm clinical trial design which includes an active and a placebo control in addition to an experimental treatment. We compare several sample size re-estimation procedures in a simulation study assessing operating characteristics including power and type I error. We find that sample size re-estimation based on the popular one-sample variance estimator results in overpowered trials. Moreover, sample size re-estimation based on unbiased variance estimators such as the Xing-Ganju variance estimator results in underpowered trials, as it is expected since an overestimation of the variance and thus the sample size is in general required for the re-estimation procedure to eventually meet the target power. Moreover, we propose an inflation factor for the sample size re-estimation with the Xing-Ganju variance estimator and show that this approach results in adequately powered trials. Due to favorable features of Xing-Ganju variance estimator such as unbiasedness and a distribution independent of the group means, the inflation factor does not depend on the nuisance parameter and, therefore, can be calculated prior to a trial.