Probabilistic Win Ratio Method For Hierarchical Composite Endpoints With Coarsened Outcomes

2026-06-05

AI Summary

Traditional win ratio methods rely on deterministic pairwise comparisons, which, under censoring or outcome-specific missingness, often misclassify unresolved matches as ties, leading to efficiency loss and bias. This work proposes a Probabilistic Win Ratio (PWR) framework that, for the first time, incorporates uncertainty quantification into win ratio estimation by replacing binary win/loss determinations with conditional probabilities. This approach assigns fractional weights to coarsely observed comparisons according to their uncertainty, automatically downweighting pairs with insufficient information while exactly recovering the classical win ratio when data are complete. The method integrates conditional probability modeling, fractional weighting, and a priority-preserving mechanism. Simulations demonstrate that PWR maintains low bias and mean squared error across various censoring and missingness scenarios, and analyses of two clinical trials confirm its calibration in nearly complete data and robustness under heavy right-censoring.

Abstract

The win ratio is increasingly used to analyze prioritized composite endpoints in clinical trials, but standard implementations rely on deterministic pairwise comparisons and can perform poorly in the presence of censoring and endpoint-specific missingness. In such settings, unresolved comparisons are often treated as ties, leading to loss of efficiency and potentially biased inference, particularly when lower-priority outcomes are incompletely observed. We propose the probabilistic win ratio (PWR), a framework for estimating the classical win ratio under coarsened observation. The PWR replaces deterministic pairwise decisions with conditional probabilities of win, loss, or tie given the observed data, allowing partially observed comparisons to contribute fractionally while being explicitly penalized according to their uncertainty. Comparisons with greater coarsening receive smaller effective weight, whereas fully observed comparisons contribute as in the classical analysis, preserving the clinical priority structure. When outcomes are fully observed, the PWR reduces exactly to the standard win ratio estimator. Simulation studies show that the PWR maintains low bias and mean squared error across a range of censoring and missingness scenarios. Two clinical trial case studies illustrate complementary data regimes, demonstrating calibration in near-complete data and stability under substantial right censoring.

Problem

• win ratio
• composite endpoints
• censoring
• missingness
• coarsened outcomes

Innovation

• probabilistic win ratio
• composite endpoints
• coarsened data
• censoring
• missingness