ROBERT J. PANZER, M.D.
To the editor: The randomized controlled trial of the effectiveness of tetracycline in the treatment of acute exacerbations of chronic bronchitis reported by Nicotra and associates(l) failed to show tetracycline superior to placebo. However, the small number of patients in the study (20 patients per group) makes the authors' conclusion that there is no difference between the two treatments unwarranted. This conclusion involves a substantial risk of a "type II" or "beta" error: concluding that there is no statistical difference when an important difference exists.
Sample size calculations based on data provided in the article show that with 20 patients
PANZER RJ. Chronic Bronchitis, Tetracycline, and Type II Error. Ann Intern Med. ;97:617. doi: 10.7326/0003-4819-97-4-617_2
Download citation file:
Published: Ann Intern Med. 1982;97(4):617.
Copyright © 2018 American College of Physicians. All Rights Reserved.
Print ISSN: 0003-4819 | Online ISSN: 1539-3704
Conditions of Use