Randomization inference for treatment effects on survival outcomes

2026-08-17

AI Summary

This study addresses the challenge of model-free treatment effect estimation in survival analysis by proposing a nonparametric confidence interval method grounded in randomization inference. By inverting the log-rank test, we construct additive and multiplicative effect intervals that rely solely on the randomization distribution, thereby eliminating dependence on traditional parametric assumptions. Simulation studies demonstrate that this approach maintains valid coverage probabilities with negligible efficiency loss, significantly enhancing inferential robustness. Furthermore, we provide comprehensive R code and an interactive Shiny application to facilitate implementation. Collectively, this work offers a reliable and accessible nonparametric statistical tool for the unbiased evaluation of treatment effects in survival data, bridging the gap between theoretical rigor and practical applicability in clinical research without requiring restrictive modeling assumptions.

Abstract

The log-rank test and Kaplan--Meier plot are standard tools for analyzing time-to-event data in randomized clinical trials, yet neither provides a summary of the magnitude of the treatment effect. Practitioners typically fill this gap by reporting a hazard ratio from a Cox proportional-hazards model or an acceleration factor from an accelerated failure time (AFT) model, but both require assumptions beyond those needed for the log-rank test or Kaplan--Meier estimator. We propose two nonparametric confidence intervals for scalar effect-size summaries, an additive shift c and a multiplicative factor $ρ$, obtained by inverting the log-rank test under sharp null hypotheses of constant treatment effects. Building on the randomization-inference framework of Li and Small (2023), both intervals are valid under the randomization distribution alone, requiring no assumptions for the event-time distribution. We evaluate the proposed multiplicative interval via simulation, finding that it maintains nominal coverage across a range of censoring rates and sample sizes, including under data-generating processes that misspecify a parametric AFT model, while incurring only a modest efficiency loss compared to parametric AFT inference under correct specification. We illustrate the approach using data from a randomized trial of rhDNase for cystic fibrosis and provide R code and a Shiny application for ease of implementation.

Problem

• survival outcomes
• treatment effect magnitude
• randomized clinical trials
• nonparametric inference
• time-to-event data

Innovation

• Randomization inference
• Nonparametric confidence intervals
• Survival outcomes
• Log-rank test inversion
• Treatment effect estimation