A menu-driven facility for sample-size calculation in novel multiarm, multistage randomized controlled trials with a time-to-event outcome

摘要: We present menu- and command-driven Stata programs for the calculation of sample size, number events, trial duration a novel type clinical design with time-to-event outcome two or more experimental arms. The approach is based on terminating accrual patients to inferior treatment arms at an early stage in trial, allowing through next only treatments that show predefined degree advantage against control treatment. first testing uses intermediate measure definitive (primary) rather than primary itself. are compared pairwise arm according measure. Arms survive comparison enter patient accrual, culminating comparisons features supported include unequal allocation, target hazard ratios may differ from 1 under null hypothesis, ability stop recruitment specified time after initiation. computations size power asymptotic mean variance log hazard-ratio alternative hypotheses. overall operating characteristics computed final significance levels power, correlation between hazard-ratios measures different stages. illustrate United Kingdom Medical Research Council six-arm prostate cancer which failure-free survival survival. © 2009 StataCorp LP.