statistical-analysis

To choose the right statistical test in Python, you can use guided decision logic for t-tests, ANOVA, regression, chi-square, and nonparametric alternatives based on your data structure. The workflow evaluates assumptions and recommends the appropriate parametric or nonparametric test for your research question.

Formatting statistical analysis results into an APA-style report requires structuring test statistics, p-values, and effect sizes into standardized result templates. This workflow automatically generates publication-ready APA-formatted result paragraphs and clear interpretation text directly from your raw data outputs.

You can run a priori power analysis and effect size calculations using pandas and scipy by computing metrics like Cohen's d, η², R², and Cramér's V. The workflow performs both a priori and sensitivity power analyses to determine required sample sizes and detectable effects.

Checking statistical assumptions like normality and homogeneity before running an ANOVA involves automated diagnostic tests and visualizations. This workflow performs normality, homogeneity, linearity, and outlier checks, providing visualizations and remediation recommendations if your data violates parametric test assumptions.

This statistical analysis workflow supports Bayesian modeling and categorical tests by providing decision guidance for chi-square tests and Bayesian options alongside traditional parametric methods. It accommodates group comparisons, regression, correlation, and categorical data within academic research workflows.