To the Editor.
—Dr Cappelleri and colleagues1 concluded that unexplained clinically important differences between the results of large trials and meta-analyses of small trials are extremely uncommon. We have several concerns with this conclusion. First, the authors based it on the results of a random effects model. While both fixed and random effects models can be useful, the interpretation of results when these models disagree is the subject of much debate.2 However, the authors note that a fixed effects model reported more disagreement between small and large studies than a random effects model. This is to be expected by the very nature of the way these 2 models address heterogeneity between studies.2 Since the a priori belief of the authors was that large trials usually support the results of meta-analyses of small trials, it appears self-serving to emphasize the results of random effects models.Second, the authors
Klebanoff MA, Levine RJ, DerSimonian R. Large Trials vs Meta-analysis of Smaller Trials. JAMA. 1997;277(5):376–377. doi:10.1001/jama.1997.03540290028024
Coronavirus Resource Center
Customize your JAMA Network experience by selecting one or more topics from the list below.