To the Editor: In their Commentary about the need for large-scale RCTs, Drs Hennekens and DeMets1 stated that meta-analyses and subgroup analyses are useful to formulate but not to test hypotheses. They argued that large-scale RCTs are the only available strategy to test a priori hypotheses. This may be understandable using a population perspective. The language of populations is the prevailing idiom of the evidence-based medicine movement, based on the evaluation of interventions, analyses of aggregated data and large sample sizes, predominance of quantitative methods, and results for average patients.
Sacristán JA. Evidence From Randomized Controlled Trials, Meta-analyses, and Subgroup Analyses. JAMA. 2010;303(13):1253-1255. doi:10.1001/jama.2010.365