Team Contingent or Sport Native? A Bayesian Analysis of Home Field Advantage in Professional Soccer

ABSTRACT

Besides confirming the existence of home advantage (HA) in professional sports competition, this work intends to breakdown HA into sub-components and trace the specific sources of HA. Using scoring performance data from ESPN FC, we fit a Bayesian multilevel-nested model to the parameters in our proposed hierarchical model of HA, allowing information obtained from the season level to inform the inferences about scoring capabilities at the upper team, league, and sport levels. Our analysis reveals that much of HA is attributed to the nature of the sport of interest as well as teams playing the sport. The results seem to endorse the view that home advantage is mainly characteristic of the sport and participating teams, while league grouping can be safely ignored as a credible contributing source. Finally, we discuss the implications of our proposed two-source model of HA for future research at the inter-sport level.

KEYWORDS:

• European professional soccer leagues
• home advantage
• Stan and CRAN-R
• predictive accuracy and Credible Intervals (CI)

Disclosure statement

No potential conflict of interest was reported by the authors.