RSS sections and groups meeting reports

Merseyside local group: Statistics of football leagues

Written by Laura Bonnett on . Posted in Sections and local group meeting reports

On 17th November 2016, the RSS Merseyside local group hosted Professor David Firth from the University of Warwick.

There were 22 people in attendance, 15 of whom were RSS members. As usual, most attendees were from the University of Liverpool. However, there were also visitors from Unilever, Liverpool Hope University, Public Health England, and the Health and Safety Executive. 

David is a professor of statistics and director of the Warwick Data Science Institute, as well as being an avid fan of Leeds United Football Club. He began his presentation by reminding the audience of the Premier League Table after the first three matches of the season, when Manchester City were at the top of the table. He then introduced a generalization of the Bradley-Terry model which yields end-of-season agreement with league standings, in balanced round-robin leagues with simple win-draw-loss points systems such as the 3-1-0 system used in association football.

David explained that this allows mid-season 'strength of schedule' differences to be eliminated coherently, in order to produce match-by-match league standings that typically are more meaningful than the familiar ranking based on accumulated points. The examples he presented seemed to capture well the intuitive opinions of those in attendance regarding which team had played the toughest schedule until that point and re-ranked teams accordingly. For example, in David’s model, after the first three matches of the season, Manchester United were ranked first despite having the same number of points as Manchester City, and an inferior goal difference since they had played a tougher schedule in the first three games.

David then presented results of work undertaken by his MSc student concerning several seasons of major European football leagues. He showed that the model was appropriate for these leagues and could be used to calibrate aspects such as the relative frequency of draws and the 'home advantage' effect. 

David concluded his talk by reminding the audience that the first time he gave this talk was at Manchester when Manchester City were at the top of the League. At the time of this talk, Liverpool are top of the league table.  Therefore, he would be pleased to accept an invitation to deliver a talk in Leeds in April, just before the end of the season (though sadly for him, the model would have to analyse the English Championship)!

The RSS Merseyside local group committee received very positive feedback on the session, and David fielded questions regarding transfer windows, new managers, alternative league tables in America, when and whether you should bet on a particular team, and whether the model could be used to compare changes in managers, etc. 

The next meeting of the RSS Merseyside Local Group will take place in February 2017 and is likely to relate to Connected Health Cities. Further details of this, and all 2017 talks, are available on our website:


Merseyside local group

Join the RSS

Join the RSS

Become part of an organisation which works to advance statistics and support statisticians

Copyright 2019 Royal Statistical Society. All Rights Reserved.
12 Errol Street, London, EC1Y 8LX. UK registered charity in England and Wales. No.306096

Twitter Facebook YouTube RSS feed RSS feed RSS newsletter

We use cookies to understand how you use our site and to improve your experience. By continuing to use our site, you accept our use of cookies and Terms of Use.