Discerning the Merit of “Significant Results”

To The Editor: The casual inspection of any journal article and its inherent focus on the study hypothesis and outcomes and not the study parameters and limitations might lead the reader to generate conclusions which were not in fact purported or supported by the study. Similarly, a quick survey of the article entitled Type-II Error Rates (Beta Errors) of Randomized Trials in Orthopaedic Trauma (2001;83:1650-5) might lead the reader to believe that there is little or no merit to randomized trials in the orthopaedic trauma literature that fail to find significant results. In fact, careful perusal of the data reveals that 433 of 620 potentially relevant study titles were eliminated because they did not meet the study criteria for eligibility, i.e., (1) published in English, (2) described as a randomized trial, (3) involving the care of adult patients with fractures, treated either operatively or nonoperatively, and (4) containing sufficient outcome information to enable calculation of study power. Considering that 39% …