This article is only available in the PDF format. Download the PDF to view the article, as well as its associated figures and tables.
—We are pleased to read of Dr Kalenak's and Dr Novack's interest in our study. We have difficulty understanding the issue that Kalenak is raising regarding power calculations. Power calculation is used, and was used in our study, to predict the sample size likely to be required to detect a significant difference between two groups—frequently, as Kalenak says, at 80% power. In reporting clinical trials, the validity of a negative study is compromised by a sample size that is insufficiently large to allow confidence in a demonstrated lack of difference between the two groups. Our study, of course, was not negative but, in fact, revealed a highly significant difference between our two groups in keeping with our prestudy sample size calculation.His second point seems to argue against his first. To perform the study described, or any study for that matter, it is important to limit the variables
Wood AJJ, Edeki T. Excessive β-Blockade With Timolol Eye Drops-Reply. JAMA. 1996;275(13):986. doi:10.1001/jama.1996.03530370023016