Modelling association football scores
- 1 September 1982
- journal article
- Published by Wiley in Statistica Neerlandica
- Vol. 36 (3) , 109-118
- https://doi.org/10.1111/j.1467-9574.1982.tb00782.x
Abstract
Abstract Previous authors have rejected the Poisson model for association football scores in favour of the Negative Binomial. This paper, however, investigates the Poisson model further. Parameters representing the teams' inherent attacking and defensive strengths are incorporated and the most appropriate model is found from a hierarchy of models. Observed and expected frequencies of scores are compared and goodness‐of‐fit tests show that although there are some small systematic differences, an independent Poisson model gives a reasonably accurate description of football scores. Improvements can be achieved by the use of a bivariate Poisson model with a correlation between scores of 0.2.Keywords
This publication has 7 references indexed in Scilit:
- The Use of Linear-Model Methodology to Rate High School or College Football TeamsJournal of the American Statistical Association, 1977
- The Use of Linear-Model Methodology to Rate High School or College Football TeamsJournal of the American Statistical Association, 1977
- On Any Given Sunday: Fair Competitor Orderings with Maximum Likelihood MethodsJournal of the American Statistical Association, 1975
- Association Football and Statistical InferenceJournal of the Royal Statistical Society Series C: Applied Statistics, 1974
- A procedure to estimate relative powers in binary contacts and an application to Dutch Football League resultsStatistica Neerlandica, 1971
- Skill and Chance in Ball GamesJournal of the Royal Statistical Society. Series A (General), 1971
- Skill and Chance in Association FootballJournal of the Royal Statistical Society. Series A (General), 1968