No Cover Image

Journal article 484 views 149 downloads

Classifying Winning Performances in International Women’s Rugby Union

Georgia Scott, Ollie Edwards, Neil Bezodis Orcid Logo, Mark Waldron Orcid Logo, Eifion Roberts, David B. Pyne Orcid Logo, Jocelyn Mara Orcid Logo, Christian Cook Orcid Logo, Laura Mason Orcid Logo, Rowan Brown Orcid Logo, Liam Kilduff Orcid Logo

International Journal of Sports Physiology and Performance, Volume: 18, Issue: 9, Pages: 1 - 7

Swansea University Authors: Georgia Scott, Neil Bezodis Orcid Logo, Mark Waldron Orcid Logo, Laura Mason Orcid Logo, Rowan Brown Orcid Logo, Liam Kilduff Orcid Logo

Abstract

Purpose: The efficacy of isolated and relative performance indicators (PIs) has been compared within Rugby Union; the latter more effective at discerning match outcomes. However, this methodology has not been applied within women’s rugby. The aim of this study was to identify PIs that maximize predi...

Full description

Published in: International Journal of Sports Physiology and Performance
ISSN: 1555-0265 1555-0273
Published: Human Kinetics
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa63875
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: Purpose: The efficacy of isolated and relative performance indicators (PIs) has been compared within Rugby Union; the latter more effective at discerning match outcomes. However, this methodology has not been applied within women’s rugby. The aim of this study was to identify PIs that maximize prediction accuracy of match outcome, from isolated and relative datasets, in Women’s Rugby Union. Methods: Twenty-six PIs were selected from 110 women’s international rugby matches between 2017-2022 to form an isolated dataset, with relative datasets determined by subtracting corresponding opposition PIs. Random forest classification was completed on both datasets, and feature selection and importance used to simplify models and interpret key PIs. Models were used in prediction on the 2021 World Cup to evaluate performance on unseen data. Results: The isolated full model correctly classified 75% of outcomes (CI (65%, 82%)), whereas the relative full model correctly classified 78% (CI (69%, 86%)). Reduced respective models correctly classified 74% (CI (65%, 82%)) and 76% (CI (67%, 84%)). Reduced models correctly predicted 100% and 96% of outcomes for isolated and relative test datasets, respectively. No significant difference in accuracy was found between datasets. Within the relative reduced model, metres made, clean breaks, missed tackles, lineouts lost, carries and kicks from hand were significant. Conclusions: Increased relative metres made, clean breaks, carries, kicks from hand, and decreased relative missed tackles and lineouts lost were associated with success. This information can be utilized to inform physical and tactical preparation and direct physiological studies in women’s rugby.
Keywords: Game Statistics, Decision Modelling, Multivariate Analysis, Team Sports, Women’s Sports.
College: Faculty of Science and Engineering
Issue: 9
Start Page: 1
End Page: 7