Identifying the performance characteristics of a winning outcome in elite mixed martial arts competition

James, Lachlan P., Robertson, Sam, Haff, G. Gregory, Beckman, Emma M. and Kelly, Vincent G. (2016) Identifying the performance characteristics of a winning outcome in elite mixed martial arts competition. Journal of Science and Medicine in Sport, 20 3: 296-301. doi:10.1016/j.jsams.2016.08.001


Author James, Lachlan P.
Robertson, Sam
Haff, G. Gregory
Beckman, Emma M.
Kelly, Vincent G.
Title Identifying the performance characteristics of a winning outcome in elite mixed martial arts competition
Journal name Journal of Science and Medicine in Sport   Check publisher's open access policy
ISSN 1440-2440
1878-1861
Publication date 2016-08-09
Year available 2016
Sub-type Article (original research)
DOI 10.1016/j.jsams.2016.08.001
Open Access Status Not yet assessed
Volume 20
Issue 3
Start page 296
End page 301
Total pages 6
Place of publication Chatswood, NSW Australia
Publisher Elsevier Australia
Language eng
Abstract To determine those performance indicators that have the greatest influence on classifying outcome at the elite level of mixed martial arts (MMA). A secondary objective was to establish the efficacy of decision tree analysis in explaining the characteristics of victory when compared to alternate statistical methods.
Formatted abstract
Objectives
To determine those performance indicators that have the greatest influence on classifying outcome at the elite level of mixed martial arts (MMA). A secondary objective was to establish the efficacy of decision tree analysis in explaining the characteristics of victory when compared to alternate statistical methods.

Design
Cross-sectional observational.

Methods
Eleven raw performance indicators from male Ultimate Fighting Championship bouts (n = 234) from July 2014–December 2014 were screened for analysis. Each raw performance indicator was also converted to a rate-dependent measure to be scaled to fight duration. Further, three additional performance indicators were calculated from the dataset and included in the analysis. Cohen’s d effect sizes were employed to determine the magnitude of the differences between Wins and Losses, while decision tree (chi-square automatic interaction detector (CHAID)) and discriminant function analyses (DFA) were used to classify outcome (Win and Loss).

Results
Effect size comparisons revealed differences between Wins and Losses across a number of performance indicators. Decision tree (raw: 71.8%; rate-scaled: 76.3%) and DFA (raw: 71.4%; rate-scaled 71.2%) achieved similar classification accuracies. Grappling and accuracy performance indicators were the most influential in explaining outcome. The decision tree models also revealed multiple combinations of performance indicators leading to victory.

Conclusions
The decision tree analyses suggest that grappling activity and technique accuracy are of particular importance in achieving victory in elite-level MMA competition. The DFA results supported the importance of these performance indicators. Decision tree induction represents an intuitive and slightly more accurate approach to explaining bout outcome in this sport when compared to DFA.
Keyword Combat sports
Performance analysis
Decision tree
Athletic performance
Discriminant function analysis
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: HERDC Pre-Audit
School of Human Movement and Nutrition Sciences Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Thu, 18 Aug 2016, 23:56:40 EST by Sandrine Ducrot on behalf of School of Human Movement and Nutrition Sciences