Abstract: In this talk we will discuss the dynamic treatment regime paradigm, its usefulness in cancer, leukemia, depression, and other complex diseases. We will demonstrate how Sequential Multiple Assignment Randomization Trials (SMART) can be used to draw inference about simple dynamic treatment regimes. Finally, applying semi-parametric theory we would construct efficient estimators for treatment regimes from simple two-stage SMART designs. The methods will be demonstrated through simulations and applications to real data from clinical trials.
