Use this skill whenever the user needs classical statistical inference or tabular machine learning for neuroimaging-derived features: OLS/GLM, Cohen's d, logistic regression, Ridge, Elastic Net, SVM/SVR, XGBoost, mixed-effects models, site-aware cross-validation, or imaging-by-treatment interactions. Triggers include 'statistical model', 'GLM', 'OLS', 'effect size', 'Cohen d', 'logistic regression', 'Ridge', 'Elastic Net', 'SVM', 'SVR', 'XGBoost', 'mixed effects', 'site split', 'tabular neuroimaging features', and 'imaging treatment interaction'.
