|
Abstract:
|
Restricted mean survival time (RMST) is often of great clinical interest. Correspondingly, regression approaches for directly modeling RMST have recently been developed. Treatment effects estimated through such models generally lack a causal interpretation in the presence of unmeasured confounding. Motivated by this issue, we propose two-stage Instrumental Variable (IV) techniques for censored data. In particular, we develop closed-form, two-stage estimators for the causal treatment effect using an additive RMST model. Large sample properties are derived, with simulation studies conducted to assess finite sample properties. We apply the proposed methods to estimate the causal effect of peritoneal dialysis among End-stage Renal Disease (ESRD) patients.
|
