Statistical Modelling 19 (1) (2019), 55–73

Ranking soccer teams on the basis of their current strength: A comparison of maximum likelihood approaches

Christophe Ley
Department of Applied Mathematics,
Computer Science and Statistics,
Faculty of Sciences,
Ghent University, Gent,
Belgium.
e-mail: Christophe.Ley@UGent.be

Tom Van de Wiele
DeepMind,
London,
United Kingdom.


Hans Van Eetvelde
Department of Applied Mathematics,
Computer Science and Statistics,
Faculty of Sciences,
Ghent University, Gent,
Belgium.


Abstract:

We present 10 different strength-based statistical models that we use to model soccer match outcomes with the aim of producing a new ranking. The models are of four main types: Thurstone–Mosteller, Bradley–Terry, independent Poisson and bivariate Poisson, and their common aspect is that the parameters are estimated via weighted maximum likelihood, the weights being a match importance factor and a time depreciation factor giving less weight to matches that are played a long time ago. Since our goal is to build a ranking reflecting the teams’ current strengths, we compare the 10 models on the basis of their predictive performance via the Rank Probability Score at the level of both domestic leagues and national teams. We find that the best models are the bivariate and independent Poisson models. We then illustrate the versatility and usefulness of our new rankings by means of three examples where the existing rankings fail to provide enough information or lead to peculiar results.

Keywords:

Bivariate Poisson model; Bradley–Terry model; Independent Poisson model; predictive performance; weighted likelihood.

Downloads:

Example data and code in zipped archive.
back