Academic Reference · 6 Definitions

Sports Analytics Glossary

Comprehensive definitions of the mathematical and statistical concepts underpinning modern sports prediction science. Each entry includes formal notation, practical application context, and worked examples from top-flight football data.

Poisson Distribution

/ˈpwɑːsɒn/

Probability Theory

P(X = k) = (λᵏ · e⁻λ) / k!

Formal Definition

The Poisson distribution is one of the most important tools in sports analytics, first formalized by French mathematician Siméon Denis Poisson in 1837. In the context of competitive sports, it describes the probability of a given number of goals, points, or discrete scoring events occurring within a defined time interval, given a known average rate (λ, lambda). The probability mass function is defined as: P(X = k) = (λ^k × e^−λ) / k! Where λ is the average rate of occurrence and k is the number of events in question.

Poisson Distribution — Goals per Match

λ = 1.48 · 5-season average · All European top divisions

λ = 1.48

Most probable outcomes (k=1,2) Other outcomes

Applied Context

In football (soccer) analytics, the average goals per team per match across Europe's top 5 leagues consistently converges near λ = 1.48. This allows analysts to compute the probability of any exact scoreline. For example, a 1–1 draw has probability approximately P(1) × P(1) ≈ 0.330 × 0.330 ≈ 10.9%, which closely mirrors empirical match frequencies over large sample sizes.

Key Properties

1Mean equals variance (both equal λ)
2Events are assumed to be independent
3Becomes approximately Normal for large λ (>10)
4Used in Dixon-Coles model for match prediction

Standard Deviation (σ)

/ˈstændəd dɪˈveɪʃən/

Descriptive Statistics

A measure of the amount of variation or dispersion of a set of values relative to their mean.

Expected Value (EV)

/ɪkˈspɛktɪd ˈvæljuː/

Decision Theory

The probability-weighted average of all possible outcomes — a fundamental concept in rational decision-making under uncertainty.

Kelly Criterion

/ˈkɛli ˈkrɪtɪrɪən/

Risk Management

A formula for determining the optimal fraction of capital to allocate to maximize long-term geometric growth.

Bayes' Theorem

/beɪz ˈθɪərəm/

Probability Theory

A mathematical formula for updating the probability of a hypothesis as more evidence or information becomes available.

Regression to the Mean

/rɪˈɡrɛʃən/

Statistical Phenomena

The tendency for extreme measurements to be followed by less extreme values on subsequent measurements.

📐

See These Concepts in Action

Our comprehensive Bankroll Management guide applies Kelly Criterion, Expected Value, and Standard Deviation to practical risk management frameworks.

Read the Guide →