A Bayesian approach for a zero modified Poisson model to predict match outcomes applied to the 2012–13 La Liga season

Abstract

In any sports competition, strong interest is devoted to the knowledge on the team that will be champion. The result of a match, the chance of a team either qualifying for a specific tournament, or relegating, the best attack and defense are all topics of interest. This paper presents a Bayesian methodology for modeling the number of goals scored by a team based on Zero-Modified Poisson distribution. An important advantage of this distribution is the flexibility in modeling count data without previous knowledge of the sampling characteristic with respect to the frequency of zeros (inflated, standard, deflation). These characteristics are present in the data sets referring to the number of goals scored by different teams. Inference procedures and computational simulation studies are also discussed. The proposed methodology was applied to the 2012–13 La Liga and the results were compared with those of the Poisson model using the De Finetti measure an percentage of correct predictions.