|
Activity Number:
|
453
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 6, 2008 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics in Sports
|
| Abstract - #302607 |
|
Title:
|
A Model of Playing Time for Pitchers in Major League Baseball
|
|
Author(s):
|
Michael Greene*+
|
|
Companies:
|
Deloitte Consulting, LLP
|
|
Address:
|
70 Burbank St Apt 18, Boston, MA, 02115,
|
|
Keywords:
|
Baseball injuries ; playing time model ; prediction of playing time
|
|
Abstract:
|
Injuries to baseball players heavily influence the statistical output of a baseball player over time. Missing time due to injuries complicates the prediction of a player's future performance. Collecting comprehensive data on injuries is difficult, thus no complete databases are available. Injured players often continue to play, which can exacerbate injuries and reduce performance. We propose a model for expected playing time for pitchers based on performance and player characteristics. The model is constructed using data from the 2005-2007 seasons and blind validation is applied to demonstrate the power of the model. This flexible model allows for the calculation of expected playing time for pitcher on a weekly basis during the season. Such a tool is useful not only for analysis, but also for teams to monitor players for possible injuries based on decreases in performance.
|
- 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 2008 program |
