Hierarchical Bayesian Modeling of Hitting Performance in Baseball - Statistics > ApplicationsReport as inadecuate




Hierarchical Bayesian Modeling of Hitting Performance in Baseball - Statistics > Applications - Download this document for free, or read online. Document in PDF available to download.

Abstract: We have developed a sophisticated statistical model for predicting thehitting performance of Major League baseball players. The Bayesian paradigmprovides a principled method for balancing past performance with crucialcovariates, such as player age and position. We share information across timeand across players by using mixture distributions to control shrinkage forimproved accuracy. We compare the performance of our model to currentsabermetric methods on a held-out season 2006, and discuss both successes andlimitations.



Author: Shane T. Jensen, Blake McShane, Abraham J. Wyner

Source: https://arxiv.org/



DOWNLOAD PDF




Related documents