Meta-analysis

A meta-analysis is a quantitative statistical technique that pools effect estimates across individual studies—usually randomized controlled trials identified by a systematic review—to produce a summary estimate with greater precision than any single study. Standard outputs include weighted mean differences or odds ratios, 95% confidence intervals, forest plots visualizing per-study and pooled estimates, and heterogeneity statistics (I², τ²) that quantify variability between studies. A seminal cannabis example is Whiting et al., JAMA 2015;313(24):2456, which pooled 79 randomized trials enrolling 6,462 participants across indications including chronic pain, chemotherapy-induced nausea and vomiting, multiple sclerosis spasticity, and sleep; the authors reported moderate-quality evidence supporting cannabinoids for chronic pain and spasticity. Only 4 of the 79 trials were judged at low risk of bias, illustrating how heterogeneity and study quality constrain confidence in pooled results. → See also: Systematic review, Cochrane review.