Doubly Robust Nonparametric Instrumental Variable Estimators for Survival Outcomes

TL;DR

This paper introduces nonparametric, doubly robust IV estimators for survival outcomes, enabling causal inference with censored data and incorporating machine learning for flexible estimation.

Contribution

It develops novel nonparametric IV estimators for survival analysis that are doubly robust and applicable to both binary and continuous instruments, filling a gap in causal inference methods.

Findings

Estimators perform well in simulations across various scenarios.

Application to cancer screening trial demonstrates practical utility.

Method effectively handles nonignorable and ignorable censoring.

Abstract

Instrumental variable (IV) methods allow us the opportunity to address unmeasured confounding in causal inference. However, most IV methods are only applicable to discrete or continuous outcomes with very few IV methods for censored survival outcomes. In this work we propose nonparametric estimators for the local average treatment effect on survival probabilities under both nonignorable and ignorable censoring. We provide an efficient influence function-based estimator and a simple estimation procedure when the IV is either binary or continuous. The proposed estimators possess double-robustness properties and can easily incorporate nonparametric estimation using machine learning tools. In simulation studies, we demonstrate the flexibility and efficiency of our proposed estimators under various plausible scenarios. We apply our method to the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial for estimating the causal effect of screening on survival probabilities and investigate the causal contrasts between the two interventions under different censoring assumptions.