To the Editor.
—Only occasionally do articles demonstrating no significant differences publish β statistics. In the trial by Weaver et al1 in which there was a 30% lower mortality rate in the patients treated in a prehospital fashion compared with the control population, there was no significant difference. According to my crude estimates, a trial of this size has about a 38% chance, almost four of 10, of not detecting even a 40% reduction in mortality given the numbers of patients studied. In other words, there is more than one chance in three that the conclusion published here is inaccurate.
Perry JJ. Prehospital-Initiated vs Hospital-Initiated Thrombolytic Therapy for Myocardial Infarction. JAMA. 1994;271(6):426. doi:10.1001/jama.1994.03510300026018
Customize your JAMA Network experience by selecting one or more topics from the list below.