Introduction to Evidence-Based Medicine William J. Powers, M.D.-- Departments of Neurology, Neurosurgery and Radiology Washington University School of Medicine -- Presented July 11, 2006
• The power of a trial is the probability that a true treatment effect of a presumed size will fail to be detected in the trial participants
• Power depends on
◊ Presumed effect size
◊ Statistical criteria for declaring a benefit
◊ Number of participants
• In a negative trial, always look at the confidence intervals for the effect size
Internet Stroke Center at Washington University: Copyright © 1997 -2007 All rights reserved.
