Bivariate Poisson model; Bradley–Terry model; Independent Poisson model; predictive performance; weighted likelihood; Statistics and Probability; Statistics, Probability and Uncertainty
Abstract :
[en] 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.
Disciplines :
Mathematics Orthopedics, rehabilitation & sports medicine
Author, co-author :
LEY, Christophe ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Mathematics (DMATH) ; Department of Applied Mathematics, Computer Science and Statistics, Faculty of Sciences, Ghent University, Gent, Belgium
Wiele, Tom Van de; DeepMind, London, United Kingdom
Eetvelde, Hans Van; Department of Applied Mathematics, Computer Science and Statistics, Faculty of Sciences, Ghent University, Gent, Belgium
External co-authors :
yes
Language :
English
Title :
Ranking soccer teams on the basis of their current strength: A comparison of maximum likelihood approaches
Angelini G, Den Agelis L, (2017) PARX model for football match predictions. Journal of Forecasting, 36, 795–807
Boshnakov G, Kharrat T, McHale IG, (2017) A bivariate Weibull count model for forecasting association football scores. International Journal of Forecasting, 33, 458–66
Bradley RA, Terry ME, (1952) Rank analysis of incomplete block designs: I. The method of paired comparisons. Biometrika, 39, 324–45
Constantinou AC, Fenton NE, (2012) Solving the problem of inadequate scoring rules for assessing probabilistic football forecast models. Journal of Quantitative Analysis in Sports, 8, 1–14
Crowder M, Dixon M, Ledford A, Robinson M, (2002) Dynamic modelling and prediction of English Football League matches for betting. Journal of the Royal Statistical Society, Series D, 51, 157–168
M. Cummings (2013) FIFA world rankings place Brazil 18th, reinforce flawed nature of system. URL https://bleacherreport.[com/articles/1488973-fifa-world][-rankings-place-brazil-18th-rei][nforce-flawed-nature-of-system] (last accessed 06 December 2018)
Curley J, (2015) engsoccerdata: Soccer data 1871-2015. R package version 0.1.4
Davidson R, (1970) On extending the Bradley–Terry model to accommodate ties in paired comparison experiments. Journal of the Royal Statistical Society, Series D (The Statistician), 65, 317–28
Dixon MJ, Coles SG, (1997) Modelling association football scores and inefficiencies in the football betting market. Journal of the Royal Statistical Society, Series C (Applied Statistics), 46, 265–80
Epstein ES, (1969) A scoring system for probability forecasts of ranked categories. Journal of Applied Meteorology, 8, 985–87
Groll A, Kneib T, Mayr A, Schauberger G, (2017) On the dependency of soccer scores: A sparse bivariate Poisson model for the UEFA European Football Championship 2016. In Proceedings of the MathSport International 2017 Conference pages, Padova, Italy, pages 161–75
Karlis D, Ntzoufras I, (2003) Analysis of sports data by using bivariate Poisson models. Journal of the Royal Statistical Society, Series D (The Statistician), 52, 381–93
Koopman SJ, Lit R, (2015) A dynamic bivariate Poisson model for analysing and forecasting match results in the English Premier League. Journal of the Royal Statistical Society, Series A (Statistics in Society), 178, 167–86
Maher M, (1982) Modelling association football scores. Statistica Neerlandica, 36, 109–18
McHale I, Scarf P, (2011) Modelling the dependence of goals scored by opposing teams in international soccer matches. Statistical Modelling, 11, 219–36
Mosteller F, (2006) Remarks on the method of paired comparisons: I. The least squares solution assuming equal standard deviations and equal correlations. In Selected Papers of Frederick Mosteller, edited by Fienberg Stephen E, Hoaglin David C, pages 157–62. New York, NY: Springer
R Development Core Team (2018) R: A lang- uage and environment for statistical computing. R Foundation for Statistical Computing. Vienna. URL http://www.[R-project.org/.] (last accessed 06 December 2018)
Scarf PA, Yusof MM, (2011) A numerical study of tournament structure and seeding policy for the soccer World Cup Finals. Statistica Neerlandica, 65, 43–57
The Associated Press (2015) Romania, Wales set to be surprise World Cup top seeds. USA Today. URL https://www.usatoday.[com/story/sports/soccer/2015/][07/23/romania-wales-set-to-be-][surprise-world-cup-top-seeds/][30563797/] (last accessed 06 December 2018)
Thurstone LL, (1927) Psychophysical analysis. The American Journal of Psychology, 38, 368–89
A. Tweedale (2015) Belgium rise to No. 1 in FIFA world rankings after they beat Israel: Despite playing one tournament in 13 years. The Telegraph. URL https://www.[telegraph.co.uk/sport/football/][teams/belgium/11928595/Belgium-][will-be-No1-in-Fifa-world-rank][ings-if-they-beat-Israel-desp ite-playing-one-tournament-in- 13-years.html] (last accessed 06 December 2018)
