In Reply Mr Adibi and colleagues raise salient points about the prior probability of replication of late-phase RCTs and the increased sample size requirements necessary for a P value threshold of .005. Although we agree that the .005 threshold would require adjustments to funding strategies and trial design, we remain unconvinced that the .005 threshold would come with “little added benefit.” Ultimately, we remain supportive of the new .005 threshold,1 for this proposal was meant to serve as a temporizing measure while improved statistical frameworks are developed.
Wayant C, Scott J, Vassar M. Lowering the P Value Threshold—Reply. JAMA. 2019;321(15):1533. doi:10.1001/jama.2019.0574
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: