statistical-analysis

You can perform statistical testing like t-tests and ANOVA, then automatically generate APA-style reports with publication-ready figures and tables. The workflow checks assumptions, calculates effect sizes with confidence intervals, and formats results for academic publication.

Yes, the skill supports Bayesian analyses using PyMC and ArviZ for statistical inference. You can fit Bayesian models, visualize posterior distributions, and run traditional frequentist tests like t-tests and ANOVA within the same workflow.

The skill automates assumption checking for normality and homogeneity of variance with visual diagnostics. It validates these statistical assumptions before running tests like ANOVA or t-tests, ensuring your hypothesis testing results are reliable.

Yes, the skill offers guidance on choosing appropriate statistical tests and conducting power analyses for planning. It helps determine required sample sizes and statistical power before data collection, ensuring robust hypothesis testing and experimental design.

Yes, pandas and scipy are required dependencies along with statsmodels, pingouin, numpy, pymc, arivz, matplotlib, and seaborn. These Python libraries provide the foundational functions for hypothesis testing, effect size calculations, and data visualization.