CMStatistics 2018: Start Registration
View Submission - CMStatistics
B1056
Title: Assessing causal effects in the presence of treatment switching through principal stratification Authors:  Alessandra Mattei - University of Florence (Italy) [presenting]
Fabrizia Mealli - University of Florence (Italy)
Peng Ding - University of California, Berkeley (United States)
Abstract: Clinical trials, focusing on survival outcomes for patients suffering from AIDS-related illnesses and painful cancers in advanced stages, often allows patients in the control arm to switch to the treatment arm if their physical conditions get worse than certain tolerance levels. The Intention-To-Treat analysis, often used in practice, provides valid causal estimates of the effect of assignment, but it does not give information about the effect of the actual receipt of the treatment and ignores the information on treatment switching. Other existing methods propose to reconstruct the outcome a unit would have had if s/he had not switched. But these methods usually rely on strong assumptions, like that there exists no relation between patients prognosis and switching behavior, or the treatment effect is constant. We propose to re-define the problem of treatment switching using principal stratification, and we focus on principal causal effects for patients belonging to subpopulations defined by the switching behavior under control. Our approach appropriately adjusts for the post-treatment information and characterizes treatment effect heterogeneity. For inference, we use a Bayesian approach to properly take into account that (i) switching happens in continuous time; (ii) switching time is not defined for units who never switch in a particular experiment; and (iii) survival time and switching time are subject to censoring. We illustrate our framework using simulated data.