@article{discovery10046121,
          number = {1},
         journal = {Stata Journal},
       publisher = {StataCorp},
            year = {2018},
           title = {Power and sample-size analysis for the Royston-Parmar combined test in clinical trials with a time-to-event outcome},
            note = {This version is the version of record. For information on re-use, please refer to the publisher's terms and conditions.},
          volume = {18},
           pages = {3--21},
        keywords = {power\_ct, randomized controlled trial, time-to-event outcome, restricted mean survival time, log-rank test, Cox test, combined test, treatment effect, hypothesis testing, flexible parametric model},
            issn = {1536-867X},
        abstract = {Randomized controlled trials with a time-to-event outcome are usually designed and analyzed assuming proportional hazards (PH) of the treatment effect. The sample-size calculation is based on a log-rank test or the nearly identical Cox test, henceforth called the Cox/log-rank test. Nonproportional hazards (non-PH) has become more common in trials and is recognized as a potential threat to interpreting the trial treatment effect and the power of the log-rank test-hence to the success of the trial. To address the issue, in 2016, Royston and Parmar (BMC Medical Research Methodology 16: 16) proposed a "combined test" of the global null hypothesis of identical survival curves in each trial arm. The Cox/logrank test is combined with a new test derived from the maximal standardized difference in restricted mean survival time (RMST) between the trial arms. The test statistic is based on evaluations of the between-arm difference in RMST over several preselected time points. The combined test involves the minimum p-value across the Cox/log-rank and RMST-based tests, appropriately standardized to have the correct distribution under the global null hypothesis. In this article, I introduce a new command, power\_ct, that uses simulation to implement power and sample-size calculations for the combined test. power\_ct supports designs with PH or non-PH of the treatment effect. I provide examples in which the power of the combined test is compared with that of the Cox/log-rank test under PH and non-PH scenarios. I conclude by offering guidance for sample-size calculations in time-to-event trials to allow for possible non-PH.},
          author = {Royston, P},
             url = {https://www.stata-journal.com/sj18-1.html}
}