[Skip to Navigation]
Access to paid content on this site is currently suspended due to excessive activity being detected from your IP address Please contact the publisher to request reinstatement.
October 1985

A Need for Statistical Review

Author Affiliations

Department of Epidemiology School of Public Health The University of North Carolina Chapel Hill, NC 27514

Am J Dis Child. 1985;139(10):962. doi:10.1001/archpedi.1985.02140120008003

Sir.—Siegel et al1 reported a randomized clinical trial of the treatment of Pneumocystis carinii pneumonitis in pediatric cancer patients.

The study design described in their article, however, does not allow the reader to evaluate critically the methods used in this clinical trial. It would be helpful to know the type I and type II errors and the clinically meaningful difference2 used to determine their sample size. What were the criteria developed for ending the trial? What was the power calculated with the reported trial size?

The lack of details about the prior planning of randomized clinical trials in the literature has been previously reported, with particular emphasis on the hazards of insufficient trial size.2 A nonsignificant result in a small trial has been stated to yield almost no information.3

Perhaps AJDC should consider adding a statistician to the Editorial Board for a more comprehensive review