Abstract:
|
The availability of pitch-tracking data has led to increased scrutiny of Major League Baseball umpires. While many studies have attempted to rate umpires based on their conformity to the rule book strike zone, players and managers tend to accept deviations from this zone, provided that umpires establish consistent zones within a game. Using tools from computational geometry, we propose new metrics for assessing the consistency and accuracy of an umpire’s ball and strike calls over the course of a game. We apply these metrics to pitch-tracking data on all ball and strike calls made during the 2017 MLB regular season, giving some characterizations of the variation in performance of MLB umpires. This analysis demonstrates that measures of consistency can complement current accuracy-based evaluations of umpires. This talk will include updates to the 2017 analysis, as well as a summary of some recent work applying these techniques to segregation measurement.
|