Abstract
ABSTRACT Analysis of key performance indicators (KPIs) in team sports has frequently involved multiple univariate analyses and modelling of direct associations between each KPI and match outcomes. This study aimed to show a more appropriate framework and modelling process to establish causal plausibility for future confirmatory studies. A cross-sectional design was adopted, using 337 team-match observations of Australian Super Rugby performances. A tentative model was developed in consultation with a domain expert (national analyst) and analysed using piecewise structural equation modelling. Model fit was assessed using Fisher’s C and the Akaike Information Criterion (AIC). Hypothesised relationships were modelled using linear mixed effects models and unmodelled pathways were investigated using tests of directed separation. The model was an acceptable fit overall, and adjustments were identified in collaboration with the national head analyst, improving the AIC from 127.15 to 120.77 (Fisher’s C = 66.78; p = 0.382). Modelling the hierarchical data structure and developing models that contain more logical hypothesised associations (in consultation with domain experts) is a more useful and important step to analyse and interpret effects of KPIs on team performance. This analysis provides support to the plausibility of the causal structure and generation of new and more precise hypotheses.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
