|
Abstract:
|
The restricted mean time in favor (RMT-IF) of treatment is a nonparametric effect size for complex life history data. The estimand is defined as the net average time the treated spend in a more favorable state than the untreated as opposed to vice versa over a fixed time window. It generalizes the familiar restricted mean survival time from the two-state life-death model to account for possible intermediate stages in disease progression. The overall estimand admits an elegant decomposition into stage-wise effects, with the standard restricted mean survival time as a component. Alternate expressions of the overall and stage-wise estimands as integrals of the marginal survival functions for a hierarchical sequence of landmark transitioning events facilitate their estimation by simple plug-in Kaplan--Meier estimators. The dynamic profile of the estimated treatment effects as a function of follow-up time can be visualized using a multilayer, cone-shaped "bouquet plot". Simulation studies under realistic settings show that the RMT-IF approach provides meaningful and accurate quantification of the treatment effect and outperforms traditional tests on time to the first event thanks to its
|
