Imperial College London
Portrait Picture

Professor Christl Donnelly CBE FMedSci FRS

Faculty of Medicine, School of Public Health

Visiting Professor
 
 
 
//

Contact

 

c.donnelly Website

 
 
//

Location

 

School of Public HealthWhite City Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Penn:2022,
author = {Penn, MJ and Donnelly, C},
journal = {PLoS One},
title = {Analysis of a double Poisson model for predicting football results in Euro 2020},
url = {https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0268511},
volume = {17},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - First developed in 1982, the double Poisson model, where goals scored by each team areassumed to be Poisson distributed with a mean depending on attacking and defensivestrengths, remains a popular choice for predicting football scores, despite the multitudeof newer methods that have been developed. This paper examines the pre-tournamentpredictions made using this model for the Euro 2020 football tournament. Thesepredictions won the Royal Statistical Society’s prediction competition, demonstratingthat even this simple model can produce high-quality results. Moreover, the paper alsopresents a range of novel analytic results which exactly quantify the conditions for theexistence and uniqueness of the solution to the equations for the model parameters.After deriving these results, it provides a novel examination of a potential problem withthe model - the over-weighting of the results of weaker teams - and illustrates theeffectiveness of ignoring results against the weakest opposition. It also compares thepredictions with the actual results of Euro 2020, showing that they were extremelyaccurate in predicting the number of goals scored. Finally, it considers the choice ofstart date for the dataset, and illustrates that the choice made by the authors (whichwas to start the dataset just after the previous major international tournament) wasclose to optimal, at least in this case. The findings of this study give a betterunderstanding of the mathematical behaviour of the double Poisson model and provideevidence for its effectiveness as a match prediction tool.
AU  - Penn,MJ
AU  - Donnelly,C
PY  - 2022///
SN  - 1932-6203
TI  - Analysis of a double Poisson model for predicting football results in Euro 2020
T2  - PLoS One
UR  - https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0268511
UR  - http://hdl.handle.net/10044/1/96695
VL  - 17
ER  -
Download