Performance indicators associated with match outcome within the United Rugby Championship. Issue 1 (January 2023)
- Record Type:
- Journal Article
- Title:
- Performance indicators associated with match outcome within the United Rugby Championship. Issue 1 (January 2023)
- Main Title:
- Performance indicators associated with match outcome within the United Rugby Championship
- Authors:
- Scott, Georgia A.
Bezodis, Neil
Waldron, Mark
Bennett, Mark
Church, Simon
Kilduff, Liam P.
Brown, M. Rowan - Abstract:
- Abstract: Objectives: The aims of this study were to: i) identify performance indicators associated with match outcomes in the United Rugby Championship; ii) compare the efficacy of isolated and relative datasets to predict match outcome; and iii) investigate whether reduced statistical models can reproduce predictive accuracy. Design: Retrospective analysis of key performance indicators in the United Rugby Championship. Methods: Twenty-seven performance indicators were selected from 96 matches (2020–21 United Rugby Championship). Random forest classification was completed on isolated and relative datasets, using a binary match outcome (win/lose). Maximum relevance and minimum redundancy performance indicator selection was utilised to reduce models. In addition, models were tested on 53 matches from the 2021–22 season to ascertain prediction accuracy. Results: Within the 2020–21 datasets, the full models correctly classified 83% of match performances for the relative dataset and 64% for isolated data, the equivalent reduced models classified 85% and 66% respectively. The reduced relative model successfully predicted 90% of match performances in the 21–22 season, highlighting that five performance indicators were significant: kicks from hand, metres made, clean breaks, turnovers conceded and scrum penalties. Conclusions: Relative performance indicators were more effective in predicting match outcomes than isolated data. Reducing features used in random forest classificationAbstract: Objectives: The aims of this study were to: i) identify performance indicators associated with match outcomes in the United Rugby Championship; ii) compare the efficacy of isolated and relative datasets to predict match outcome; and iii) investigate whether reduced statistical models can reproduce predictive accuracy. Design: Retrospective analysis of key performance indicators in the United Rugby Championship. Methods: Twenty-seven performance indicators were selected from 96 matches (2020–21 United Rugby Championship). Random forest classification was completed on isolated and relative datasets, using a binary match outcome (win/lose). Maximum relevance and minimum redundancy performance indicator selection was utilised to reduce models. In addition, models were tested on 53 matches from the 2021–22 season to ascertain prediction accuracy. Results: Within the 2020–21 datasets, the full models correctly classified 83% of match performances for the relative dataset and 64% for isolated data, the equivalent reduced models classified 85% and 66% respectively. The reduced relative model successfully predicted 90% of match performances in the 21–22 season, highlighting that five performance indicators were significant: kicks from hand, metres made, clean breaks, turnovers conceded and scrum penalties. Conclusions: Relative performance indicators were more effective in predicting match outcomes than isolated data. Reducing features used in random forest classification did not degrade prediction accuracy, whilst also simplifying interpretation for practitioners. Increased kicks from hand, metres made, and clean breaks compared to the opposition, as well as fewer scrum penalties and turnovers conceded were all indicators of winning match outcomes within the United Rugby Championship. … (more)
- Is Part Of:
- Journal of science and medicine in sport. Volume 26:Issue 1(2023)
- Journal:
- Journal of science and medicine in sport
- Issue:
- Volume 26:Issue 1(2023)
- Issue Display:
- Volume 26, Issue 1 (2023)
- Year:
- 2023
- Volume:
- 26
- Issue:
- 1
- Issue Sort Value:
- 2023-0026-0001-0000
- Page Start:
- 63
- Page End:
- 68
- Publication Date:
- 2023-01
- Subjects:
- MDA mean decrease accuracy -- MRMR maximum relevance, minimum redundancy -- OOB out of bag -- PI performance indicator -- RFC random forest classification
Game statistics -- Decision modelling -- Multivariate analysis -- Sports performance -- Team sports
Sports sciences -- Periodicals
Sports medicine -- Periodicals
Exercise -- Physiological aspects -- Periodicals
Sports -- physiology -- Periodicals
Sports Medicine -- Periodicals
Sportgeneeskunde
617.102705 - Journal URLs:
- http://www.sciencedirect.com/science/journal/14402440 ↗
http://www.elsevier.com/journals ↗ - DOI:
- 10.1016/j.jsams.2022.11.006 ↗
- Languages:
- English
- ISSNs:
- 1440-2440
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 5054.840000
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 24949.xml