A comparison of rating systems for competitive women's beach volleyball

Abstract

Women’s beach volleyball became an official Olympic sport in 1996 and continues to attract the participation of amateur and professional female athletes. The most well-known ranking system for women’s beach volleyball is a non-probabilistic method used by the Fédération Internationale de Volleyball (FIVB) in which points are accumulated based on results in designated competitions. This system produces rankings which, in part,
determine qualification to elite events including the Olympics. We investigated the application of several alternative probabilistic rating systems for head-to-head games as an approach to ranking women’s beach volleyball teams. These include the Elo (1978) system, the Glicko (Glickman, 1999) and Glicko-2 (Glickman, 2001) systems, and the Stephenson (Stephenson and Sonas, 2016) system, all of which have close connections to the Bradley Terry (Bradley and Terry, 1952) model for paired comparisons. Based on the full set of FIVB volleyball competition results over the years 2007-2014, we optimized the parameters for these rating systems based on a predictive validation approach. The probabilistic rating
systems produce 2014 end-of-year rankings that lack consistency with the FIVB 2014 rankings. Based on the 2014 rankings for both probabilistic and FIVB systems, we found that match results in 2015 were less predictable using the FIVB system compared to any of the probabilistic systems. These results suggest that the use of probabilistic rating systems may provide greater assurance of generating rankings with better validity.