Group Sequential Crossover Trial Designs with Strong Control of the Familywise Error Rate

TL;DR

This paper introduces a method to control the familywise error rate in group sequential crossover trials, enabling more efficient trial designs with potential reductions in observations.

Contribution

It provides a formal proof for strong control of the familywise error rate in group sequential crossover trials analyzed with linear mixed models, a novel integration.

Findings

Strong control of familywise error rate established

Formulae for expected sample size derived

Potential 33% reduction in observations demonstrated

Abstract

Crossover designs are an extremely useful tool to investigators, whilst group sequential methods have proven highly proficient at improving the efficiency of parallel group trials. Yet, group sequential methods and crossover designs have rarely been paired together. One possible explanation for this could be the absence of a formal proof of how to strongly control the familywise error rate in the case when multiple comparisons will be made. Here, we provide this proof, valid for any number of initial experimental treatments and any number of stages, when results are analysed using a linear mixed model. We then establish formulae for the expected sample size and expected number of observations of such a trial, given any choice of stopping boundaries. Finally, utilising the four-treatment, four-period TOMADO trial as an example, we demonstrate group sequential methods in this setting could have reduced the trials expected number of observations under the global null hypothesis by over 33%.