*********************************************************************

      M.Sc. in STOCHASTICS and DATA SCIENCE

     http://www.master-sds.unito.it/do/home.pl

 

        UNIVERSITA' DEGLI STUDI DI TORINO

*********************************************************************

Martedì 9 Maggio 2017 alle ore 11:30 in Aula 12 (Corso Unione Sovietica 

218/bis, School of Management and Economics), nell'ambito delle attività 

previste per il corso di Statistics for Stocahstic Processes

            il Prof. Christophe Ley  (Ghent University, Belgio)

terrà un seminario dal titolo

An alternative ranking for national soccer teams based on strength parameters

Abstract:

The FIFA ranking of national (male) soccer teams suffers from various 

drawbacks that cause heated  debates, all-the-more  as  this  ranking 

governs the seating in the international tournaments and the associated 

qualification rounds. In the present paper, we propose five alternative 

models based on strength parameters that are determined by maximum 

likelihood estimation. We conduct a comparison of these five statistical 

models, to which we add the ELO model used for the women's FIFA ranking, 

on grounds of their predictive performance. Indeed, contrary to regular 

league rankings, the FIFA ranking is designed to measure the current 

strength of teams, hence should allow accurate predictions of future 

matches. Our comparison is based on fifteen English Premier League seasons. 

The best performing model is then used to build the alternative FIFA 

ranking. We furthermore show its predictive power by analyzing the 2016 

European Championship and comparing our predictions to the bookmaker 

ratings, usually considered as golden standard.

Tutti gli interessati sono invitati a partecipare.