statistical-analysis

Hypothesis testing requires pre-specified hypotheses, assumption verification, and effect size reporting to prevent p-hacking. This Skill enforces disciplined workflows, calculates confidence intervals, and ensures results are both statistically and practically significant before final inference.

A/B test analysis needs rigorous independent t-tests with effect size calculation and 95% confidence interval reporting. This Skill applies assumption checks to your test data, eliminating false positives and ensuring valid, trustworthy inference for your business intelligence use cases.

Regression and time series decomposition are supported for research data inference. The Skill processes descriptive statistics, probability distributions, and correlation modeling while enforcing assumption checks to deliver validated analytical results.

Homogeneity of variances verification is enforced before running ANOVA tests. This Skill mandates assumption checks, selects the correct parametric or non-parametric test, and runs post-hoc Tukey tests with effect sizes to support publishable findings.

Non-parametric hypothesis testing is fully supported alongside parametric tests. The Skill enforces rigorous inference guardrails across both testing types, calculating confidence intervals and effect sizes to avoid false positives in your statistical workflows.

Statistical analysis requires pre-specified hypotheses and confidence intervals to avoid false positives and p-hacking. This Skill mandates these guardrails alongside effect size calculation, ensuring your data inference is both statistically and practically significant.