Ranking Sports Teams: More Than Just a Statistics Project

• Activity Number: 224
• Type: Invited
• Date/Time: Monday, August 10, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics in Sports
• Author(s): Michael A. Rutter*
• Companies: Penn State Erie, The Behrend College
• Keywords: Sports ; Undergraduate ; Rankings

Abstract

When undergraduates look for research projects, rankings are often a popular topic. In the past, these types of projects were static, relying on one years worth of data to create a ranking system for the end of the season (for a sport, like college hockey) or for one point in time (for a game of skill, like chess). And while the statistical methodology needed to create a viable ranking system is an important part of the project, there are additional skills that can be learned that can be extremely useful for a young statistician. Scraping data from on-line resources, real-world data manipulation, and automation are just some of the skills that a student can acquire during a ranking project. While the data sets created by such projects are not on the same scale as the "big data" found in commercial applications, the techniques learned by doing small-scale undergraduate research projects are valuable and applicable to today's job market.