This is the abstract of the paper:
The aims of this study were to
identify variables which may potentially influence player performance, and to implement a statistical model to study
their relative contribution in order to explain two outcomes: points and win
score. We used all the possible variables affecting player performance creating
a comprehensive database from two sources of statistical information about the
NBA 2007 regular season: www.basketball-reference.com and www.nbastuffer.com. The data employed for the analysis
were composed of 2187 cases (27 players * 81 games), having followed a
filtering process. We dealt with a balanced study design with repeated
measurements given that each player was observed the same number of games, and
therefore the player was considered as a random effect. We carried out mixed
models to quantify the variability in points and win score among players.
Minutes played, the usage percentage and the difference of quality between
teams were the main factors for variations in points made and win score. The
interaction between player position and age was important in win score. We
encourage managers and coaches of sports teams to choose appropriate methods
according to their aims. Future research should take into consideration the use
of models with random effects on players’ characteristics.
And this is the full reference of the paper
Casals, M. & Martínez, J. A. (2013). Modelling player performance in basketball through mixed models. International Journal of Performance Analysis in Sport, 13 (1), 64-82.
http://www.ingentaconnect.com/content/uwic/ujpa/2013/00000013/00000001/art00007