LEONARD E. BRAITMAN, PH.D.
Many clinicians and medical researchers are unsure how to interpret data that do not pass tests of statistical significance. Because a nonsignificant result does not imply that there is no effect or no difference, it is important to make "the distinction between positively demonstrating that a treatment had no effect and failing to demonstrate that it does have an effect . . ." (1). In clinical trials, the lack of efficacy of a new treatment sometimes is inferred from a nonsignificant difference between outcomes in treatment and placebo groups. Such inferences are invalid without consideration of the ability of the
BRAITMAN LE. Statistical Power Analysis in Medical Research. Ann Intern Med. 1983;99:269–271. doi: 10.7326/0003-4819-99-2-269
Download citation file:
Published: Ann Intern Med. 1983;99(2):269-271.
Results provided by:
Copyright © 2018 American College of Physicians. All Rights Reserved.
Print ISSN: 0003-4819 | Online ISSN: 1539-3704
Conditions of Use