Answers are grounded in this paper and cite their sources.
The purpose of this study is to estimate win statistics (win ratio, win odds, and net benefit) under non-informative censoring for prioritized composite outcomes. Survival data with non-informative censoring, independent of the distribution of survival times, were considered, involving a binary treatment variable and prioritized composite outcomes. In this context, a model-based imputation (MBI) method for estimating win statistics is proposed. This method utilizes a conditional survival distribution derived from the Kaplan-Meier (KM) estimator to impute the survival times of censored individuals. The proposed method adjusts for censoring bias by imputing survival times using the KM estimator under non-informative censoring. Simulation results showed that the proposed method had less bias than both the unadjusted method and the inverse probability of censoring weighting (IPCW) method, while maintaining comparable empirical variance to IPCW. The simulation study demonstrated consistent results across varying sample sizes and censoring rates. MBI methods are proposed for two or more prioritized composite endpoints under non-informative censoring. These methods effectively adjust for bias caused by missing data due to censoring in prioritized composite outcomes while maintaining variability comparable to IPCW, making them useful for estimating win statistics.
No takes yet. Share an insight, caveat, or question.
Jeong et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: