Statistics for Sports Data

Sports arguments are statistics arguments in disguise. This course builds the measurement vocabulary — what a distribution is, when a mean lies, how to standardize across eras, where a hot streak is real and where it's noise — always computed by you, on real data, never quoted from authority.

It ends deliberately on correlation and regression: after ten tutorials of describing data, the capstone asks the question every fan actually cares about — which numbers predict winning, and how would you know?

What you'll be able to do

• Summarize any stat honestly: center, spread, shape, outliers
• Standardize with z-scores and percentiles to compare across teams and eras
• Smooth time series with rolling windows and EWMA without erasing the signal
• Run and read a regression, and know its limits

Download the course bundle - every script + dataset, one ZIP

The bundle contains each part's finished script, the shared helpers, and the sample data they read, with a README listing the run order - the whole course works offline.

The syllabus

Pace: Sequential through part 8; the time-series pair and the regression capstone close it out. Three weeks at a sitting each.

1. 1Summary Statistics and Distributions with pandasBeginner · ~5 minCenter, spread and shape - the three questions to ask any column first.
2. 2Box Plots: Comparing Distributions Across GroupsBeginner · ~5 minThe five-number summary as a picture; comparisons come free.
3. 3Standardize Stats with Z-Scores: Compare Columns on One ScaleIntermediate · ~5 minThe universal translator: any stat, any era, one scale.
4. 4Percentile Ranks and Tiers: Locate a Team in the DistributionIntermediate · ~5 minWhere a value sits in the pack, in units everyone understands.
5. 5Binning Continuous Data into Categories with pd.cut()Beginner · ~5 minContinuous to categorical, honestly - tiers without cherry-picking.
6. 6The ECDF: Read Any Percentile Off a Cumulative CurveIntermediate · ~5 minThe whole distribution in one curve, no bins to argue about.
7. 7Measuring Inequality: Lorenz Curves and the Gini CoefficientIntermediate · ~5 minHow concentrated is scoring? Inequality has a number.
8. 8Outlier Detection: IQR Fences and the Modified Z-ScoreIntermediate · ~5 minA defensible rule for 'weird', instead of squinting at it.
9. 9Rolling Averages and Form: Time-Series Basics for SportsIntermediate · ~7 minForm is a moving window; learn what the window hides.
10. 10Exponentially Weighted Averages: Form That Weights Recent Games MoreIntermediate · ~5 minRecency weighting done right - and when it beats a plain rolling mean.
11. 11Correlation and Regression: What Actually Predicts Winning?Advanced · ~8 minThe capstone question: which numbers actually predict winning?

Check yourself

Five questions, graded on the page, nothing recorded anywhere - pick an answer and the explanation appears.

Where next: Randomness, Inference & Simulation · Machine Learning from Scratch.