statistical-analysis

Hypothesis testing for ANOVA is supported alongside automatic assumption checking to verify test validity and provide diagnostic visualizations. You can execute t-tests, chi-square tests, and non-parametric alternatives while ensuring your data meets the required statistical assumptions.

Effect size and power analysis are fully supported to help calculate effect sizes, confidence intervals, and determine required sample sizes. This allows you to quantify the magnitude of relationships and ensure your research design has adequate statistical power.

Bayesian regression analysis is supported using the pymc and arviz dependencies for computation and visualization. You can conduct linear, multiple, and logistic regression analyses alongside traditional frequentist approaches within the same workflow.

APA-style statistical reports and tables are generated automatically after conducting your hypothesis testing and regression analysis. This feature formats your scientific results according to APA standards, streamlining the academic research reporting process.

Correlation analysis and scientific reporting require scipy, statsmodels, pingouin, pymc, and arviz dependencies. These libraries provide the computational backbone for measuring relationships between variables and generating visualizations for your research data.

Comprehensive statistical analysis for academic research is provided through a toolkit supporting hypothesis testing, regression, correlation, and effect size calculations. It is specifically designed for research workflows involving data analysis and scientific reporting.