|
Activity Number:
|
410
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 12, 2004 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics in Sports
|
| Abstract - #300815 |
|
Title:
|
Football Performance Plots
|
|
Author(s):
|
James M. Lucas*+
|
|
Companies:
|
J.M. Lucas and Associates
|
|
Address:
|
5120 New Kent Rd., Wilmington, DE, 19808,
|
|
Keywords:
|
winning percentage ; CUSUM
|
|
Abstract:
|
We evaluate the performance of college football programs and coaches using football performance plots. These plots show the strong effect of coaches on a teams winning percentage. In this they clearly show an effect that is known to exist. The sensitivity of these plots also allows an assistant coach effect to be discovered. The winning percentage of football teams can be strongly influenced by a superior assistant coach. Formally, a football performance plot is a CUSUM that plots: Cumulative Wins - (k) Cumulative Games versus Cumulative Games. The empirically determined reference value (k) is team- and coach-dependent. For strong programs a reference value of 0.75 works well as few football programs have had a winning percentage this high. For outstanding coaches a reference value of 0.8 often works well. Two examples of an assistant coach effect: Bobby Bowden had a 70.6% winning record at Samford, West Virginia, for his first 11 years at Florida State. While Mark Richt was an assistant coach, his winning percentage was 88.9%. Since Richt has left his winning percentage has reverted to its lower level. Joe Paterno's career winning percentage is above 75%.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2004 program |
