Glossary › Poisson model

Definition

Poisson model

The statistical distribution that turns each side's expected goals into a probability for every scoreline.

Why it fits football

Goals are rare, roughly independent events with a stable average — exactly what the Poisson distribution describes. Given an expected 1.6 goals, it outputs the probability of scoring 0, 1, 2, 3…

How it becomes a prediction

Apply Poisson to both teams and multiply: P(home scores i) × P(away scores j) fills the matrix cell for scoreline i-j. Summing cells yields 1X2, over/under, BTTS and exact-score probabilities from one consistent object.

FAQ

Who first used Poisson for football?

Analyses go back to Morley's 1958 study of World Cup scoring; it has been the standard starting point ever since.

Is plain Poisson enough?

It under-rates low-score draws — which is why the Dixon-Coles correction exists.