| Abstract : | The aim of this research is to specify and estimate models for football players' performance. Using these models, a rating index will be constructed for each player position, so that each players' contribution to the game can be comparable to one another. The position specialization is indispensable, since in each position the effectiveness of a player in special statistical categories is more important than in others. Each model will be a function of all the statistical measures that OLS regression will indicate as important. Although rating indices exist in other sports, such ratings do not exist in football. We will use the simulation video game Football Manager (FM), which provides the most updated real players database, as source of the needed data. In this game the user coaches a football team, dealing with transfers, training and game tactics, having as his main goal the teams’ success. Two seasons were played by the author and all the individual players’ statistics after each game, including the rating that FM provides, were collected by hand. The model selection, for each of the six positions, was performed via the combination of cross-validation technique, stepwise procedure and the use of information criteria. The models’ estimated coefficients were used, combined with the official players’ statistics of Tottenham Hotspur of the two previous seasons (English Premier League, FA Cup, League Cup games), in order to evaluate each player’s performance and identify the most valuable players. Furthermore, the impact of position performance to the outcome of the game was examined through ordered Probit and Logit analysis. Finally, the impact of the Tottenham Hotspur players’ season average ratings to their weekly wages and their market values was investigated.
|
|---|
Copyright © 2013 Library AUEB. All rights reserved.