A Bayesian asymmetric logistic model of factors underlying team success in top‐level basketball in Spain

Abstract

This paper analyses the factors underlying the victories and defeats of the Spanish basketball teams Real Madrid and Barcelona in the national league, ACB. The following research questions were addressed: (a) Is it possible to identify the factors underlying these results? (b) Can knowledge of these factors increase the probability of winning and thus help coaches take better decisions? We analysed 80 and 79 games played in the 2013-2014 season by Real Madrid and Barcelona, respectively. Logistic regression analysis was performed to predict the probability of the team winning. The models were estimated by standard (frequentist) and Bayesian methods, taking into account the asymmetry of the data, that is, the fact that the database contained many more wins than losses. Thus, the analysis consisted of an asymmetric logistic regression. From the Bayesian standpoint, this model was considered the most appropriate, as it highlighted relevant factors that might remain undetected by standard logistic regression. The prediction quality of the models obtained was tested by application to the results produced in the following season (2014)(2015).field. In short, asymmetric logistic regression is a valuable tool that can help coaches improve their game strategies. KEYWORDS asymmetric link, Bayesian estimation, logistic regression, model selection INTRODUCTIONIn sports clubs, as in all organisations, decisions must be taken in order to maintain and, if possible, improve performance. Quantitative methods can be used to assist in the decision-making process and thus avoid excessive subjectivity. In the context of professional sports, the emergence of the "Moneyball phenomenon" (Lewis, 2004) has produced many changes in the use of information sources. The main focus of this approach is to measure the contributions made by each player, from the data generated during a game, in order to optimise available resources and thus improve the team's performance.Sports decisions, regarding the team design, transfers, or new signings (of players or coaches), are restricted by the economic limitations facing the organisation. Clearly, wealthier clubs have greater possibilities of signing elite athletes and thus of buying better performance. Clubs with fewer resources, however, might counter this imbalanced situation by analysing quantitative information in order to sign the best human resources possible in accordance with the available budget or to detect and exploit their opponents' weaknesses. However, the "Moneyball philosophy" cannot readily be extrapolated to basketball, due to the great complexity of this sport. Innumerable factors may influence the performance of a player and his team, such as the opponent (defence tactics, types of players, pace, etc.), teammates' abilities, the team's playing style, the coach's philosophy, and the stage of the match. Certainly, it is very complicated to measure all these aspects using only the traditional box score. In response, much has been done to improve the quality and quantity of available i...

Research on basketball game tactics based on multivariate statistical methods

“…Root, Hayley J. argued that proper basketball training could reduce the injury rate of athletes in games and improve neuromuscular control [16]. Perez-Sanchez, J et al developed a method to help coaches make better decisions by analyzing the factors influencing the win and loss of Spanish basketball against Real Madrid, combined with logistic regression analysis predictions [17].…”