|
How to reassess the efficacy and demonstrate the robustness of treatment effect with scientific sound methods is a challenging task for statisticians. In Immuno-Oncology clinical trials, treatment effect tends to be confound by delayed drug effect or crossing survival curves. In this presentation, different Non-parametric or semi-parametric approaches including milestone, weighted logrank, etc. are exercised. Survival curves with crossing and delayed effected are simulated for analysis purpose. Type I error control and power were studied through simulations Results show similar treatment effect and demonstrate the drug efficacy. Statistical inference based on p-values and confidence intervals of adjusted clinical endpoints take into consideration.
Methods will be recommended under different scenarios. The further development in this area can not only demonstrate the robustness of efficacy, but also help improving the efficiency in decision making in Phase I/II studies and access more information for pivotal study design.
|
