Effect of Misspecification on a Multi Treatment Two Stage Adaptive Design for Survival Outcomes

Multi-treatment two stage adaptive design for survival responses is generally developed under different assumptions. In this work, we explore the performance of such a design when the assumptions are violated. As a choice of design, we consider a specific design of Bhattacharya and Shome (2019), which uses random censoring, exponential response, Koziol-Green model (Koziol and Green, 1976), etc. Several ethical and inferential criteria of the design are studied under model misspecification for different parameter configurations as well as for a data arising from a real clinical trial. IJSS, Vol. 24(2) Special, December, 2024, pp 67-79