Font Size: 

The basic assumption in modelling football outcomes is that the number
of goals scored by both the teams follow two independent Poisson distributions, or
possible generalizations allowing for a positive correlation between them. Scores’
data are regularly used for the estimation of the attack and the defence strength of
each team. However, these teams’ abilities are quite complex and are correlated with
many quantities inherent to the game. Additional available information, relevant for
estimating attack and defence parameters, are shots, both made and conceded. For
such a reason, we propose a model that allows to incorporate this information in
three stages for each game and each team: number of scores, number of shots on
target and number of total shots.We collected historical data arising from 10 seasons
of the English Premier League, from 2007-2008 to 2016-2017, and we fit the model
assessing its goodness of fit through posterior predictive checks. Secondly, we made
predictions for a set of future matches and we compared our posterior probabilities
with those obtained from the bookmakers.