A Bayesian Hierarchical Model for Estimating the Cost of Postponing the Cyclocross National Championships

• Activity Number: 184
• Type: Contributed
• Date/Time: Monday, August 10, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Sports
• Author(s): James Fry* and Andrew Hoegh and Scotland Leman and Matt Montesano
• Companies: Virginia Tech and Virginia Tech and Virginia Tech and
• Keywords: Bayesian ; mixed model ; cyclocross ; sport ; cycling ; hierarchical

Abstract

In early January 2015, the multi-event national cyclocross bicycle races were set to take place in Austin, TX. Cyclocross has a rich history in this country, and throughout the world, attracting huge crowds and competitors. Being primarily a winter sport, these athletes often compete in harsh conditions, which include rain, snow, mud, and revel in the excitement that comes with such elements. Unfortunately, the competition was postponed mid-event due a local arborist group protesting to the parks department. This issue: there was too much mud, in an event where spectators and racers alike hope for such conditions. The arborist group argued that the increase in mud exposed the root systems of many trees, leaving them open to damage from bicycles. The postponement generated additional expenses for many competitors, such as flights, hotels, and car rentals. We analyze the financial impact of the disagreement using a hierarchical Bayesian mixed model which accounts for heterogeneity within the costs endured by the event's participants.