Improving Power of the Win Ratio Analysis through Distance-based Weights

The win ratio method, used to analyze composite endpoints in clinical trials, has gained substantial popularity in recent years because of its ability to prioritize components of the composite outcome. Despite gaining popularity and being extended to solve some of its issues, little work has been done to incorporate covariate information into the win ratio. In this article, we extend the win ratio method by incorporating weights to each win or loss based on the distance between the compared pair using their covariate values. This approach aims to improve the power of the original win ratio when the covariates used for computing the weights are associated with the components of the composite outcome. Through detailed simulation studies and real data analyses, we demonstrate the utility of our proposed method. In general, our simulation studies indicate that the proposed method is more powerful when covariates used to calculate the weights are associated with the outcomes, and it performs similarly to the original method when there is no such association.