A Statistical Analysis of Team Defense and Performance in the National Hockey League

Abstract

In this paper, I explore the relationship between goalkeeper and team performance in professional hockey using statistical models. The model is evaluated by checking for outliers and major assumptions of the ordinary least squares regression model. I find a negative relationship between goals allowed per game and total team points per season. In particular, I find that the intercept of the model to be 184.0 and coefficient for average goals allowed per game to be -33.819. This means that when goals allowed per game increases by 0.1, the total points for a team in a season will decrease by 3.38. The assumptions of the linear regression model are satisfied. 

Keywords

• Hockey,Sports Analytics,Statistics,Linear Regression,Ordinary Least Squares

References

1. Lames M, McGarry T (2007). On the search for reliable performance indicators in game sports. International Journal of Performance Analysis in Sport. 7(1):62-79.
2. Ofoghi B, Zeleznikow J, MacMahon C, Raab M (2013). Data Mining in Elite Sports: Measurement in Physical Education and Exercise Science. 17(3):171-186.
3. Reilly T (2001). Assessment of sports performance with particular reference to field games. European Journal of Sport Science. 1(3):1-12.
4. Seaton M, Campos J (2017). Distribution competence of a football clubs goalkeepers. International Journal of Performance Analysis in Sport. 11(2):314-324.
5. Travassos B, Davids K, Araujo D, Esteves TP (2013). Performance analysis in team sports: Advances from an Ecological Dynamics approach. International Journal of Performance Analysis in Sport. 13(1):83-95.