Statistical analyses of basketball team performance: understanding teams’ wins and losses according to a different index of ball possessions

Jaime Sampaio and Manuel Janeira

International Journal of Performance Analysis in Sport, 2003, vol. 3, issue 1, 40-49

Abstract: The aim of the present paper is to investigate the discriminatory power of game statistics between winning and losing teams in the Portuguese Professional Basketball League. Methodological issues concerning game rhythm contamination and data organization according to game type (regular season or play-off), game final outcome (win or loss), game location (home or away) and game final score differences are discussed. Archival data were obtained for the 1997-1998 and the 1998-1999 Portuguese Professional Basketball League seasons for (a) all 353 regular season home and away games and (b) all 56 play-off home and away games. Cluster analysis was conducted to establish, according to game final score differences, three different groups for the subsequent analysis (close games, with final score differences between 1 and 8 points; balanced games, with final score differences between 8 and 18 points and unbalanced games, with final score differences above 18 points). Afterwards, discriminant analysis was used to identify the game statistics that maximize mean differences between winning and losing teams according to previously defined factors (type, location, cluster groups). Obtained results allowed us to understand that in balanced and unbalanced games, losing teams performed poorly in all game statistics. In contrast, results from close games allowed us to identify different team performance profiles according to game type and location. Globally, regular season profile was best discriminated by successful free-throws, whereas play-offs profile was best discriminated by offensive rebounding. On the other hand, home wins were best discriminated by committed fouls whereas successful free-throws discriminated away wins. Coaches and players should be aware of these different profiles in order to increase specificity at the time of game planning and control.

Date: 2003
References: View complete reference list from CitEc
Citations: View citations in EconPapers (9)

Downloads: (external link)
http://hdl.handle.net/10.1080/24748668.2003.11868273 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:rpanxx:v:3:y:2003:i:1:p:40-49

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/RPAN20

DOI: 10.1080/24748668.2003.11868273

Access Statistics for this article

International Journal of Performance Analysis in Sport is currently edited by Peter O'Donoghue

More articles in International Journal of Performance Analysis in Sport from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().