Abstract:
|
There are well-known dangers for performing subgroup analyses for clinical trials. In this paper, we propose a systematic method for testing and identifying a subgroup with an enhanced treatment effect. We adopts change-plane analysis to first test the existence of subgroups, and then identify subgroups if the null hypothesis on non-existence of such subgroups is rejected. We consider a semiparametric model for the response with an unspecified baseline function and an interaction between a subgroup indicator and treatment. A doubly-robust test statistic is constructed based on this model, and asymptotic distributions of the test statistic under both null and local alternative hypotheses are derived. We show the validity of the test both theoretically and numerically. Furthermore, we develop a sample size calculation method for the proposed test, which is established based on the asymptotic distributions of the test statistic. Finally, the proposed method on subgroup identification and the sample size calculation are applied to data from an AIDS study.
|
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.