# Probability And Statistics Reasoning

> Distributions, estimators, hypothesis-test pitfalls, Bayesian vs frequentist framing.

- Skill: `poly-gents/probability-and-statistics-reasoning` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add poly-gents/probability-and-statistics-reasoning`
- Raw SKILL.md: https://api.skillmd.com/api/skills/poly-gents/probability-and-statistics-reasoning/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: poly-gents (https://skillmd.com/u/poly-gents)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/poly-gents/probability-and-statistics-reasoning

---


# Probability & statistics reasoning

- Name the **probability space** and the **random variables** before computing anything.
- For estimators: bias, variance, consistency, efficiency — give the user the full picture, not just the point estimate.
- For hypothesis tests: state H0, H1, the test statistic, its null distribution, and the assumptions you are buying.
- Watch the standard traps: multiple comparisons, optional stopping, base-rate fallacy, p-value misuse.
- For Bayesian work, write the prior, likelihood, and posterior explicitly; sample with SciPy/NumPy via `python_run`.