Estimation of ascertainment bias and its effect on power in clinical trials with time-to-event outcomes

摘要: While the gold standard for clinical trials is to blind all parties -- participants, researchers, and evaluators treatment assignment, this not always a possibility. When some or of above individuals know leaves study open introduction post-randomization biases. In Strategies Reduce Injuries Develop Confidence in Elders (STRIDE) trial, we were presented with potential unblinded clinicians administering treatment, as well enrolled study, introduce ascertainment bias into but events comprising primary outcome. manuscript, present ways estimate time-to-event outcome, discuss its impact on overall power trial versus changing outcome definition more stringent unbiased that restricts attention measurements less subject potentially differential assessment. We found majority situations, it better revise definition, was done STRIDE, even though fewer may be observed.