Key variables for predicting scoring success in Brazilian basketball games

Abstract

The objective of this study was to identify the variables that can predict the number of points scored by teams in Brazil's national basketball league. A total of 182 NBB games were analyzed using scouting variables including free-throw, 2-point, and 3-point shooting percentages; free-throw, 2-point, and 3-point attempts; number of defensive and offensive rebounds; number of assists, steals, turnovers, violations, and fouls committed and received. A Multiple Linear Regression analysis (SPSS, v.19) was used to determine which variables predict the number of points scored in a game. The prediction of the number of points scored was achieved (a) without considering shooting variables, (b) considering only shooting-related variables, and (c) considering all analyzed variables, explaining 30.5%, 62.9%, and 63.2% of the variation in scoring behavior, respectively. These findings can be used to enhance basketball training by focusing on the most determinant variables for scoring in games.