Summary statistics of football matches such as final score, possession and percentage of completed passes are not satisfyingly informative about style of play seen on the pitch. In this sense, networks and graphs are able to quantify how teams play differently from each others. We study the distribution of triad census, i.e., the distribution of local structures in networks and we show how it is possible to characterize passing networks of football teams. We describe the triadic structure and analyse its distribution under some specific probabilistic assumptions, introducing, in this context, some tests to verify the presence of specific triadic patterns in football data. We first run an omnibus test against a random structure to asses whether the observed triadic distribution deviates from randomness. Then, we redesign the Dirichlet-Multinomial test to recognize different triadic behaviours after choosing some reference patterns. The proposed tests are applied to a real dataset regarding 288 matches in the Group Stage of the UEFA Champions League over three consecutive seasons.
Testing styles of play using triad census distribution: an application to men’s football / Palazzo, Lucio; Ievoli, Riccardo; Ragozini, Giancarlo. - In: JOURNAL OF QUANTITATIVE ANALYSIS IN SPORTS. - ISSN 2194-6388. - 19:2(2023), pp. 125-151. [10.1515/jqas-2022-0010]
Testing styles of play using triad census distribution: an application to men’s football
Lucio PalazzoPrimo
;Riccardo IevoliSecondo
;Giancarlo RagoziniUltimo
2023
Abstract
Summary statistics of football matches such as final score, possession and percentage of completed passes are not satisfyingly informative about style of play seen on the pitch. In this sense, networks and graphs are able to quantify how teams play differently from each others. We study the distribution of triad census, i.e., the distribution of local structures in networks and we show how it is possible to characterize passing networks of football teams. We describe the triadic structure and analyse its distribution under some specific probabilistic assumptions, introducing, in this context, some tests to verify the presence of specific triadic patterns in football data. We first run an omnibus test against a random structure to asses whether the observed triadic distribution deviates from randomness. Then, we redesign the Dirichlet-Multinomial test to recognize different triadic behaviours after choosing some reference patterns. The proposed tests are applied to a real dataset regarding 288 matches in the Group Stage of the UEFA Champions League over three consecutive seasons.File | Dimensione | Formato | |
---|---|---|---|
10.1515_jqas-2022-0010.pdf
solo utenti autorizzati
Licenza:
Non specificato
Dimensione
1.48 MB
Formato
Adobe PDF
|
1.48 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.