The post challenges the notion that effect sizes below 0.50 for medications are clinically insignificant, using antidepressants as a case study and comparing them to other common drugs. Longer summary

This post discusses the interpretation of effect sizes in medical studies, particularly for antidepressants. It challenges the common notion that effect sizes below 0.50 are clinically insignificant. The author presents a Danish study that simulates various hypothetical medications, showing that even drugs that cure or significantly improve depression in a large percentage of patients might not meet traditional effect size thresholds. The post explains why these thresholds might be unrealistic due to factors like the placebo effect, high standard deviations in placebo groups, and patient dropouts. It also compares antidepressant effect sizes to those of other widely accepted medications, concluding that many common drugs would be considered 'clinically insignificant' by strict effect size standards. The author suggests that claims about 'meaningless effect sizes' should be given less weight compared to other evidence, such as clinical experience. Shorter summary