Interim Analyses Using the Curtailed Win-Ratio

Music City Center 

The win-ratio, a term introduced by Pocock et. al. (2012), has become a popular approach to the statistical analysis of controlled clinical trials with multiple prioritized point outcomes. Briefly, comparisons of the time to the primary outcome (say mortality) are made between each subject in the active treatment group and each subject in the control group with indeterminacies resolved where possible by comparisons of times to secondary outcomes. This approach usually gives similar results to the conventional analysis based on the time to the first event, but it has the conceptual advantage of basing the comparison on the more important outcome when the results for the two outcomes differ. See Oakes (2025) for further discussion of the properties of the win-ratio statistic. As noted by Finkelstein and Schoenfeld (2018), the changing composition of the win-ratio statistic over time makes it hard to interpret interim analyses of accumulating data or to develop rules for interim stopping. Oakes (2016) proposed a curtailed win-ratio statistic, based on data accumulated on each subject up to a prespecified window (say one-year of follow-up). This approach avoids the difficulty and allows conventional sequential stopping rules to be used.