MetaAnalysis Run

Run a fixed-effects or random-effects meta-analysis from a set of effect sizes and standard errors. Uses inverse-variance weighting for fixed effects and the DerSimonian-Laird estimator for random effects. Returns pooled effect size with 95% CI, p-value, heterogeneity statistics (Cochran Q, I-squared, tau-squared), per-study weights, and a text interpretation. Pure local computation -- no external API calls. Useful for combining results from multiple studies in systematic reviews.