Activity Number:
|
193
- Contributed Poster Presentations: Section on Statistics in Sports
|
Type:
|
Contributed
|
Date/Time:
|
Monday, July 30, 2018 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistics in Sports
|
Abstract #330807
|
|
Title:
|
Equipment Independent Estimation of Novel Metrics for Ranking Amateur Auto Racing Drivers
|
Author(s):
|
Alexandra Peterson* and Daniel L. Gillen and Hal Stern
|
Companies:
|
and University of California, Irvine and University of California, Irvine
|
Keywords:
|
NASCAR;
Ranking;
Mixed Effects;
Driver Ability
|
Abstract:
|
NASCAR race teams continuously strive to identify skilled drivers at younger age levels in order to identify and foster talent into professional racing. However, ranking driver performance based upon finishing position is heavily impacted by the quality of equipment and crews at a driver's disposal. This is particularly true at younger ages where there exist higher disparities in equipment quality. As such a common goal of many NASCAR race teams is to identify drivers based upon inherent ability. We propose new metrics for ranking drivers based upon their ability to pass competitors (offense) and to prevent competitors from passing them (defense). Utilizing lap-to-lap time, position, cumulative time, and practice lap data from multiple amateur events, we employ generalized linear mixed models to estimate driver-specific random effects that are then used to rank drivers by their offensive and defensive ability. Our approach explicitly accounts for equipment quality in estimating driver abilities. Empirical simulation results are also presented to verify that these metrics are strong indicators of long-term driver performance.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2018 program
|