Application of Statistics in Sports: Predicting How Teams Win Games In NBA

Presentation Format: 
Scientific Paper Oral Presentation
Masaru Teramoto, University of Nevada, Las Vegas
Chad L. Cross, University of Nevada, Las Vegas

Introduction: “The quantitative analysis of sports is a new branch of science” (Kubatko et al., 2007, p. 20). Utilizing quantitative methods, we can measure, evaluate, and predict performance in sports. In this study, we examined how teams win games in the National Basketball Association (NBA) using statistical analysis. Methods and Analysis: The relationships of several performance factors to winning games in the NBA were analyzed using correlation and regression analyses. The performance factors chosen for the analyses included traditional basketball statistics (e.g., field goal percentage, rebounds per game) as well as recently developed basketball statistics (e.g., overall efficiency, the Four Factor) (Oliver, 2004). Results: Efficient offense and defense are both essential to be successful in the regular season and the playoffs, but the importance of defense in winning games may be greater in the playoffs than in the regular season. Committing fewer turnovers and rebounding, especially later in the post-season, could be other keys to winning games. Conclusions and Reflection: It appears that overall efficiency and the Four Factor can capture a team’s performance better than traditional basketball statistics. The results of the data analysis indicate that the regular season and the playoffs in the NBA may be different ball games.


Kubatko, J., Oliver, D., Pelton, K., & Rosenbaum, D. T. (2007). A starting point for analyzing basketball statistics. Journal of Quantitative Analysis in Sports, 3(3), Article 1.
Oliver, D. (2004). Basketball on paper: Rules and tools for performance analysis. Washington, DC: Brassey's, Inc.

Thursday, October 14, 2010 - 8:30am - 9:20am
Washoe EF