Performance indicator ranking and predictive modelling in rugby union.

The aim of this study is to increase the body of knowledge surrounding Northern Hemisphere rugby union by establishing norms for performance indicators; forming a ranking of performance indicators in terms of their importance to successful team performance on a game by game and seasonal basis; in addition creating a predictive model that can forecast domestic league success. Match statistics from 132 men’s domestic matches played over the 2014/15 season of the Aviva Premiership were analysed. Team performance indicators representing frequencies of a given event for each team in each match were divided into six categories: attack, defence, kicking, breakdown, set pieces and discipline. Statistics from each of the 132 matches were then inputted into Microsoft Excel and subsequently IBM SPSS Statistics for Windows (version 22) software for statistical analysis. The performance indicators were used to highlight key differences between winning and losing performances as well as team ranking on a game by game and seasonal basis. It was found that in accordance to previous research, clean breaks are crucial to successful rugby performance as they often lead to some form of score, and scoring often reflects game outcome (Hughes et al., 2012). Also the need for penalty limitation and effective set pieces, to maintain possession and limit the scoring opportunities of the opposition, (Askew, 2010; Higham, 2014; Hughes et al., 2012) has been supported. Finally, a significant (P