Scott Evans and Mark Glickman
The 2017 New England Symposium on Statistics in Sports (NESSIS) was held September 23 at the Harvard University Science Center. The symposium format was a mixture of invited talks, a poster session, and a panel discussion.
NESSIS was established by Mark Glickman and Scott Evans to enhance the communication and collaboration between statisticians and quantitative analysts connected with sports teams, sports media, and universities. The first NESSIS was held in 2007 with 110 attendees primarily from the New England area. Continued enthusiasm inspired NESSIS to be held biannually.
The 2017 NESSIS drew a diverse crowd of 245 registrants, including attendees from at least seven countries and 33 states.
NESSIS was highlighted by featured talks. First, David Firth of the University of Warwick and the Alan Turing Institute spoke about fair standings in soccer and other round-robin leagues through retrodictive modeling. The second featured talk was a presentation by Stephanie Kovalchik of Tennis Australia on a shot taxonomy in the era of tracking data in professional tennis. Another featured talk was delivered by co-presenters Michael Lopez of Skidmore College and Ben Baumer of Smith College, titled “How Often Does the Best Team Win? A Unified Approach to Understanding Randomness in North American Sport.”
NESSIS also featured a panel discussion, “Past, Present, and Future of Analytics in the NFL,” consisting of panelists Dennis Lock of the Miami Dolphins, Karim Kassam of the Pittsburgh Steelers, and Sandy Weil of the Los Angeles Rams. Aaron Schatz of Football Outsiders served as moderator.
Abstract submissions to NESSIS included statistical applications to baseball, basketball, football, hockey, tennis, golf, soccer, cricket, volleyball, Australian football, and more. Abstracts were critically screened to keep content quality high. Peer-reviewed NESSIS proceedings will be published in two tracks. Papers focused on methodology were invited for submission to the Journal of Quantitative Analysis in Sports, while application-focused papers were invited for submission to the Journal of Sports Analytics. All presenters were invited to submit.
The motivation for a sports statistics symposium is predicated on the need for advanced analytic methods in games and sports. The application of statistical methods in sports is rapidly growing. Sports teams use statistical analyses to evaluate players and game strategies, and sports associations develop ranking and ratings systems of players and teams. The evolution of the application of statistics to sports is enhanced with extensive collaboration and interaction between sports analysts and professional statisticians. Unfortunately, opportunities for this collaboration are still relatively uncommon, as academic statisticians often work in isolation developing statistical methods for sports applications, while sports organizations often have limited access to advanced statistical expertise and cutting-edge statistical tools for the analysis of sports data. The main goal of NESSIS is to bridge this gap.
NESSIS was sponsored by the American Statistical Association (ASA), Statistics in Sports Section of the ASA, Boston Chapter of ASA, Harvard University Department of Statistics, ESPN Analytics, DeGruyter, and IOS Press.
The NESSIS founders hope the enthusiasm generated from NESSIS will increase the collaboration between academic statisticians and analysts connected with sports teams and improve the quality of statistical design and analysis in sports. Future NESSIS events will encourage the development of cutting-edge statistical thinking in sports applications and adaptations to evolving data-collection technologies.
Leave a Reply