Track

Statistics, taught with oil & energy data

A complete introductory-to-advanced statistics course compressed into twelve visual chapters. Every example is a real analysis of an open energy dataset — crude prices, refinery runs, exploration wells, oil fields and national energy balances — and every number on the pages is computed from that data.

12 chapters + 3 toolkit pages ~6 hours SQL (PostgreSQL) + Python Level: beginner → advanced

The course

Tutorial · Energy edition

Statistics for Daily Use

Descriptive statistics, probability, sampling distributions, confidence intervals, hypothesis tests, chi-square, regression, ANOVA — then bootstrap, Bayes and the traps of real time-series data.

The data behind it

Dataset	Publisher	Used for
Brent & WTI daily spot prices (1987–today)	U.S. Energy Information Administration	Returns, volatility, fat tails, paired comparisons
Weekly crude stocks, refinery utilisation, retail gasoline	U.S. EIA	Tests, ANOVA, regression from crude to the pump
Exploration wells, field reserves, monthly production	Norwegian Offshore Directorate (FactPages)	Probability, binomial/Poisson, χ², CLT, bootstrap, Bayes
Country energy panel	Our World in Data (Energy Institute Statistical Review et al.)	Populations vs samples, skewed distributions
Monthly commodity prices since 1960	World Bank "Pink Sheet"	Correlation across oil, gas and coal

Details, licences and how to rerun every analysis: Data, Code & Reproducibility.