statistical-analysis

Hypothesis testing with t-tests and ANOVA compares means across groups to determine statistical significance. This Skill automates test selection, execution, assumption verification, and generates effect sizes with APA-style reporting using scipy, statsmodels, and pingouin libraries.

Assumption checks validate normality, homoscedasticity, and independence before hypothesis testing. This Skill verifies these prerequisites automatically and flags violations, ensuring test validity and guiding you toward appropriate alternatives when assumptions fail.

Effect sizes and power analysis quantify practical significance and required sample sizes. This Skill computes effect sizes for all test types and runs power analyses to plan study design, supporting publication requirements and research planning.

APA-style reporting formats test results, confidence intervals, and effect sizes to publication standards. This Skill produces ready-to-use reports with visualizations via matplotlib and seaborn, eliminating manual formatting.

Regression analysis and Bayesian statistics extend hypothesis testing to continuous predictors and probabilistic inference. This Skill covers both approaches using statsmodels for regression and arviz for Bayesian diagnostics and visualization.