Crossover design in clinical trials for binary response

Abstract

In this paper, we consider a binary response model for the analysis of the two-treatment, two-period and four-sequence crossover design. We have introduced intra-patient drug dependency parameter in the model and provide two tests for the hypothesis of equality of treatment effects. We employ Monte Carlo simulation to compare our tests and a test that works under parallel design on the basis of type I error rate and power. We find that our procedures are dominant over the competitor with respect to power. Finally, we use a data set to illustrate the applicability of our procedure.

Keywords:

• binary responses
• crossover design
• parallel design
• logistic model
• likelihood function
• Rao's score test

Acknowledgements

The authors acknowledge the editor and the anonymous referees for their suggestions and valuable comments.

Disclosure statement

No potential conflict of interest was reported by the author(s).