Efficient and Debiased Learning of Average Hazard Under Non-Proportional Hazards

TL;DR

This paper introduces a new method for estimating the average hazard rate in survival analysis that remains valid and interpretable even when hazards are non-proportional, using a flexible, machine learning-enabled, doubly robust approach.

Contribution

It develops a semiparametric, doubly robust framework for covariate-adjusted average hazard estimation with valid inference, addressing limitations of existing methods under non-proportional hazards.

Findings

Estimator achieves small bias in simulations

Provides valid confidence intervals under complex hazard scenarios

Demonstrates utility in real-world melanoma treatment data

Abstract

The hazard ratio from the Cox proportional hazards model is a ubiquitous summary of treatment effect. However, when hazards are non-proportional, the hazard ratio can lose a stable causal interpretation and become study-dependent because it effectively averages time-varying effects with weights determined by follow-up and censoring. We consider the average hazard (AH) as an alternative causal estimand: a population-level person-time event rate that remains well-defined and interpretable without assuming proportional hazards. Although AH can be estimated nonparametrically and regression-style adjustments have been proposed, existing approaches do not provide a general framework for flexible, high-dimensional nuisance estimation with valid sqrt{n} inference. We address this gap by developing a semiparametric, doubly robust framework for covariate-adjusted AH. We establish pathwise differentiability of AH in the nonparametric model, derive its efficient influence function, and construct cross-fitted, debiased estimators that leverage machine learning for nuisance estimation while retaining asymptotically normal, sqrt{n}-consistent inference under mild product-rate conditions. Simulations demonstrate that the proposed estimator achieves small bias and near-nominal confidence-interval coverage across proportional and non-proportional hazards settings, including crossing-hazards regimes where Cox-based summaries can be unstable. We illustrate practical utility in comparative effectiveness research by comparing immunotherapy regimens for advanced melanoma using SEER-Medicare linked data.