Do larger studies find smaller effects? The example of studies for the prevention of conduct disorder

Introduction There is some emerging evidence in medicine that larger clinical trials tend to be associated with smaller effect sizes. Much of the evidence-base currently informing practice in Child Psychiatry relies on relatively small trials. We therefore investigated the relationship between trial size and effect size in research within a key area of child mental health. Method A recent systematic review of 20 trials of prevention of conduct disorder was subjected to meta-regression, to examine the relationship between study size and effect size, and to explore hypothesised confounding variables. Results In this sample of studies, reported effect size was inversely related to sample size. This effect is not explained by year of publication, intervention type or quality of methodology in the study. Discussion Our finding is consistent with other reports in the literature. The origin of this effect is not yet clear. However if replicated it clearly has significant implications for the way trials in child mental health are interpreted.