Abstract:
|
We consider a situation where more than one endpoint is viewed as important to evaluate interventions’ effects in a clinical trial and the trial is designed to evaluate a joint effect on all of the endpoints as co-primary. For co-primary endpoints, failure to demonstrate statistical significance on any single endpoint implies that test intervention’s effect to control cannot be concluded. When evaluating the endpoints as co-primary, the hypothesis test is conservative, especially when the number of endpoints being evaluated is large and the correlations among the endpoints are small. Also, the Type II error rate increases as the number of endpoints being evaluated increases or the correlations among the endpoints are smaller. These may result in a sample size that is too large and impractical to conduct the clinical trial. To overcome this issue, we discuss several group-sequential strategies to testing two co-primary endpoints to evaluate if an experimental treatment is superior to a control on both outcomes. We investigate the operating characteristics of strategies in term of the power, Type I error, and sample sizes. We illustrate the approaches using a real clinical trial.
|