No Cover Image

Journal article 518 views 286 downloads

Descriptive conversion of performance indicators in rugby union / Mark Bennett, Neil Bezodis, David A. Shearer, Duncan Locke, Liam Kilduff

Journal of Science and Medicine in Sport, Volume: 22, Issue: 3, Pages: 330 - 334

Swansea University Authors: Neil Bezodis, Liam Kilduff

Abstract

ObjectivesThe primary aim of this study was to examine whether accuracy of rugby union match prediction outcomes differed dependent on the method of data analysis (i.e., isolated vs. descriptively converted or relative data). A secondary aim was to then use the most appropriate method to investigate...

Full description

Published in: Journal of Science and Medicine in Sport
ISSN: 1440-2440
Published: 2019
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa43255
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2018-08-13T18:15:56Z
last_indexed 2020-07-08T19:04:16Z
id cronfa43255
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2020-07-08T15:00:52.1401409</datestamp><bib-version>v2</bib-version><id>43255</id><entry>2018-08-13</entry><title>Descriptive conversion of performance indicators in rugby union</title><swanseaauthors><author><sid>534588568c1936e94e1ed8527b8c991b</sid><ORCID>0000-0003-2229-3310</ORCID><firstname>Neil</firstname><surname>Bezodis</surname><name>Neil Bezodis</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>972ed9a1dda7a0de20581a0f8350be98</sid><ORCID>0000-0001-9449-2293</ORCID><firstname>Liam</firstname><surname>Kilduff</surname><name>Liam Kilduff</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2018-08-13</date><deptcode>STSC</deptcode><abstract>ObjectivesThe primary aim of this study was to examine whether accuracy of rugby union match prediction outcomes differed dependent on the method of data analysis (i.e., isolated vs. descriptively converted or relative data). A secondary aim was to then use the most appropriate method to investigate the performance indicators (PI&#x2019;s) most relevant to match outcome.MethodsData was 16 PI&#x2019;s from 127 matches across the 2016&#x2013;17 English Premiership rugby season. Given the binary outcome (win/lose), a random forest classification model was built using these data sets. Predictive ability of the models was further assessed by predicting outcomes from data sets of 72 matches across the 2017&#x2013;18 season.ResultsThe relative data model attained a balanced prediction rate of 80% (95% CI &#x2013; 75&#x2013;85%) for 2016&#x2013;17 data, whereas the isolated data model only achieved 64% (95% CI &#x2013; 58&#x2013;70%). In addition, the relative data model correctly predicted 76% (95% CI &#x2013; 68&#x2013;84%) of the 2017&#x2013;18 data, compared with 70% (95% CI &#x2013; 63&#x2013;77%) for the isolated data model. From the relative data model, 10 PI&#x2019;s had significant relationships with game outcome; kicks from hand, clean breaks, average carry distance, penalties conceded when the opposition have the ball, turnovers conceded, total metres carried, defenders beaten, ratio of tackles missed to tackles made, total missed tackles, and turnovers won.ConclusionsOutcomes of Premiership rugby matches are better predicted when relative data sets are utilised. Basic open-field abilities based around an effective kicking game, ball carrying abilities, and not conceding penalties when the opposition are in possession are the most relevant predictors of success.</abstract><type>Journal Article</type><journal>Journal of Science and Medicine in Sport</journal><volume>22</volume><journalNumber>3</journalNumber><paginationStart>330</paginationStart><paginationEnd>334</paginationEnd><publisher/><issnPrint>1440-2440</issnPrint><keywords>Team sport, Random forest, Performance indicators, Partial dependence plots</keywords><publishedDay>31</publishedDay><publishedMonth>3</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-03-31</publishedDate><doi>10.1016/j.jsams.2018.08.008</doi><url/><notes/><college>COLLEGE NANME</college><department>Sport and Exercise Sciences</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>STSC</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2020-07-08T15:00:52.1401409</lastEdited><Created>2018-08-13T09:06:03.5123652</Created><path><level id="1">College of Engineering</level><level id="2">Sports Science</level></path><authors><author><firstname>Mark</firstname><surname>Bennett</surname><order>1</order></author><author><firstname>Neil</firstname><surname>Bezodis</surname><orcid>0000-0003-2229-3310</orcid><order>2</order></author><author><firstname>David A.</firstname><surname>Shearer</surname><order>3</order></author><author><firstname>Duncan</firstname><surname>Locke</surname><order>4</order></author><author><firstname>Liam</firstname><surname>Kilduff</surname><orcid>0000-0001-9449-2293</orcid><order>5</order></author></authors><documents><document><filename>0043255-13082018090746.pdf</filename><originalFilename>kilduff2018(2).pdf</originalFilename><uploaded>2018-08-13T09:07:46.8500000</uploaded><type>Output</type><contentLength>355227</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2019-08-18T00:00:00.0000000</embargoDate><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2020-07-08T15:00:52.1401409 v2 43255 2018-08-13 Descriptive conversion of performance indicators in rugby union 534588568c1936e94e1ed8527b8c991b 0000-0003-2229-3310 Neil Bezodis Neil Bezodis true false 972ed9a1dda7a0de20581a0f8350be98 0000-0001-9449-2293 Liam Kilduff Liam Kilduff true false 2018-08-13 STSC ObjectivesThe primary aim of this study was to examine whether accuracy of rugby union match prediction outcomes differed dependent on the method of data analysis (i.e., isolated vs. descriptively converted or relative data). A secondary aim was to then use the most appropriate method to investigate the performance indicators (PI’s) most relevant to match outcome.MethodsData was 16 PI’s from 127 matches across the 2016–17 English Premiership rugby season. Given the binary outcome (win/lose), a random forest classification model was built using these data sets. Predictive ability of the models was further assessed by predicting outcomes from data sets of 72 matches across the 2017–18 season.ResultsThe relative data model attained a balanced prediction rate of 80% (95% CI – 75–85%) for 2016–17 data, whereas the isolated data model only achieved 64% (95% CI – 58–70%). In addition, the relative data model correctly predicted 76% (95% CI – 68–84%) of the 2017–18 data, compared with 70% (95% CI – 63–77%) for the isolated data model. From the relative data model, 10 PI’s had significant relationships with game outcome; kicks from hand, clean breaks, average carry distance, penalties conceded when the opposition have the ball, turnovers conceded, total metres carried, defenders beaten, ratio of tackles missed to tackles made, total missed tackles, and turnovers won.ConclusionsOutcomes of Premiership rugby matches are better predicted when relative data sets are utilised. Basic open-field abilities based around an effective kicking game, ball carrying abilities, and not conceding penalties when the opposition are in possession are the most relevant predictors of success. Journal Article Journal of Science and Medicine in Sport 22 3 330 334 1440-2440 Team sport, Random forest, Performance indicators, Partial dependence plots 31 3 2019 2019-03-31 10.1016/j.jsams.2018.08.008 COLLEGE NANME Sport and Exercise Sciences COLLEGE CODE STSC Swansea University 2020-07-08T15:00:52.1401409 2018-08-13T09:06:03.5123652 College of Engineering Sports Science Mark Bennett 1 Neil Bezodis 0000-0003-2229-3310 2 David A. Shearer 3 Duncan Locke 4 Liam Kilduff 0000-0001-9449-2293 5 0043255-13082018090746.pdf kilduff2018(2).pdf 2018-08-13T09:07:46.8500000 Output 355227 application/pdf Accepted Manuscript true 2019-08-18T00:00:00.0000000 true eng
title Descriptive conversion of performance indicators in rugby union
spellingShingle Descriptive conversion of performance indicators in rugby union
Neil, Bezodis
Liam, Kilduff
title_short Descriptive conversion of performance indicators in rugby union
title_full Descriptive conversion of performance indicators in rugby union
title_fullStr Descriptive conversion of performance indicators in rugby union
title_full_unstemmed Descriptive conversion of performance indicators in rugby union
title_sort Descriptive conversion of performance indicators in rugby union
author_id_str_mv 534588568c1936e94e1ed8527b8c991b
972ed9a1dda7a0de20581a0f8350be98
author_id_fullname_str_mv 534588568c1936e94e1ed8527b8c991b_***_Neil, Bezodis
972ed9a1dda7a0de20581a0f8350be98_***_Liam, Kilduff
author Neil, Bezodis
Liam, Kilduff
author2 Mark Bennett
Neil Bezodis
David A. Shearer
Duncan Locke
Liam Kilduff
format Journal article
container_title Journal of Science and Medicine in Sport
container_volume 22
container_issue 3
container_start_page 330
publishDate 2019
institution Swansea University
issn 1440-2440
doi_str_mv 10.1016/j.jsams.2018.08.008
college_str College of Engineering
hierarchytype
hierarchy_top_id collegeofengineering
hierarchy_top_title College of Engineering
hierarchy_parent_id collegeofengineering
hierarchy_parent_title College of Engineering
department_str Sports Science{{{_:::_}}}College of Engineering{{{_:::_}}}Sports Science
document_store_str 1
active_str 0
description ObjectivesThe primary aim of this study was to examine whether accuracy of rugby union match prediction outcomes differed dependent on the method of data analysis (i.e., isolated vs. descriptively converted or relative data). A secondary aim was to then use the most appropriate method to investigate the performance indicators (PI’s) most relevant to match outcome.MethodsData was 16 PI’s from 127 matches across the 2016–17 English Premiership rugby season. Given the binary outcome (win/lose), a random forest classification model was built using these data sets. Predictive ability of the models was further assessed by predicting outcomes from data sets of 72 matches across the 2017–18 season.ResultsThe relative data model attained a balanced prediction rate of 80% (95% CI – 75–85%) for 2016–17 data, whereas the isolated data model only achieved 64% (95% CI – 58–70%). In addition, the relative data model correctly predicted 76% (95% CI – 68–84%) of the 2017–18 data, compared with 70% (95% CI – 63–77%) for the isolated data model. From the relative data model, 10 PI’s had significant relationships with game outcome; kicks from hand, clean breaks, average carry distance, penalties conceded when the opposition have the ball, turnovers conceded, total metres carried, defenders beaten, ratio of tackles missed to tackles made, total missed tackles, and turnovers won.ConclusionsOutcomes of Premiership rugby matches are better predicted when relative data sets are utilised. Basic open-field abilities based around an effective kicking game, ball carrying abilities, and not conceding penalties when the opposition are in possession are the most relevant predictors of success.
published_date 2019-03-31T03:59:14Z
_version_ 1717642937964167168
score 10.841665