The performance of a two-stage analysis of ABAB/BABA crossover trials

TL;DR

This paper evaluates a two-stage method for constructing confidence intervals in ABAB/BABA crossover trials, finding it unreliable due to poor coverage probability, similar to previous findings in AB/BA trials.

Contribution

It extends analysis of two-stage confidence interval procedures to ABAB/BABA crossover trials, demonstrating their inadequacy despite differences from AB/BA designs.

Findings

Two-stage procedure has sub-nominal coverage probability.

Unbiased estimator of carryover effect in ABAB/BABA trials does not improve interval reliability.

Method should not be used for crossover trial analysis.

Abstract

Freeman has considered the following two-stage procedure for finding a confidence interval for the treatment difference theta, using data from an AB/BA crossover trial. In the first stage, a preliminary test of the null hypothesis that the differential carryover is zero, is carried out. If this hypothesis is accepted then the confidence interval for theta is constructed assuming that the differential carryover is zero. If, on the other hand, this hypothesis is rejected then this confidence interval is constructed using only data from the first period. Freeman has shown that this confidence interval has minimum coverage probability far below nominal. He therefore concludes that this confidence interval should not be used. In the present paper, we analyse the performance of a similar two-stage procedure for an ABAB/BABA crossover trial. This trial differs in very significant ways from an AB/BA crossover trial, including the fact that for an ABAB/BABA crossover trial there is an unbiased estimator of the differential carryover that is unaffected by between-subject variation. Despite these great differences, we arrive at the same conclusion as Freeman. Namely, that the confidence interval resulting from the two-stage procedure should not be used.