In-season prediction of batting averages: a field test of empirical Bayes and Bayes methodol\-ogies

DOI10.1214/07-AOAS138SUPPMaRDI QIDQ2482971zbMATH OpenFDO

Authors Lawrence Brown

Publication date 30 April 2008

Published in The Annals of Applied Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0803.3697

zbMATH Keywords

empirical BayesFDRharmonic priorhierarchical Bayeshitting streakshot-handsportsvariance stabilization

Mathematics Subject Classification ID

Empirical decision procedures; empirical Bayes procedures (62C12) Bayesian inference (62F15) Nonparametric inference (62G99) Applications of statistics (62P99)

Abstract: Batting average is one of the principle performance measures for an individual baseball player. It is natural to statistically model this as a binomial-variable proportion, with a given (observed) number of qualifying attempts (called ``at-bats), an observed number of successes (``hits) distributed according to the binomial distribution, and with a true (but unknown) value of $p_i$ that represents the player's latent ability. This is a common data structure in many statistical applications; and so the methodological study here has implications for such a range of applications. We look at batting records for each Major League player over the course of a single season (2005). The primary focus is on using only the batting records from an earlier part of the season (e.g., the first 3 months) in order to estimate the batter's latent ability, $p_i$, and consequently, also to predict their batting-average performance for the remainder of the season. Since we are using a season that has already concluded, we can then validate our estimation performance by comparing the estimated values to the actual values for the remainder of the season. The prediction methods to be investigated are motivated from empirical Bayes and hierarchical Bayes interpretations. A newly proposed nonparametric empirical Bayes procedure performs particularly well in the basic analysis of the full data set, though less well with analyses involving more homogeneous subsets of the data. In those more homogeneous situations better performance is obtained from appropriate versions of more familiar methods. In all situations the poorest performing choice is the na"{{i}}ve predictor which directly uses the current average to predict the future average.

Recommendations

• Estimation with Selected Binomial Information or Do You Really Believe That Dave Winfield is Batting .471?
• scientific article; zbMATH DE number 1031815
• scientific article; zbMATH DE number 775737
• Bayes and Empirical Bayes Procedures for Comparing Parameters
• Model-based estimation of baseball batting metrics

Cites work

• A test for the Poisson distribution
• Admissible Estimators, Recurrent Diffusions, and Insoluble Boundary Value Problems
• Estimation of the mean of a multivariate normal distribution
• Estimation with Incompletely Specified Loss Functions (the Case of Several Location Parameters)
• Estimation with quadratic loss.
• Estimators for Gaussian models having a block-wise structure
• scientific article; zbMATH DE number 1634843 (Why is no real title available?)
• scientific article; zbMATH DE number 3124366 (Why is no real title available?)
• scientific article; zbMATH DE number 3557007 (Why is no real title available?)
• scientific article; zbMATH DE number 1220667 (Why is no real title available?)
• scientific article; zbMATH DE number 720689 (Why is no real title available?)
• scientific article; zbMATH DE number 3205757 (Why is no real title available?)
• scientific article; zbMATH DE number 3068128 (Why is no real title available?)
• Nonparametric empirical Bayes and compound decision approaches to estimation of a high-dimensional vector of normal means
• Proper Bayes Minimax Estimators of the Multivariate Normal Mean
• Robbins, empirical Bayes and microarrays
• Statistical decision theory and Bayesian analysis. 2nd ed
• Tables of the Freeman-Tukey transformations for the binomial and Poisson distributions
• The Efficiency of Logistic Regression Compared to Normal Discriminant Analysis
• The General Canonical Correlation Distribution
• The root-unroot algorithm for density estimation as implemented via wavelet block thresholding
• THE TRANSFORMATION OF POISSON, BINOMIAL AND NEGATIVE-BINOMIAL DATA
• Transformations Related to the Angular and the Square Root

Cited in

(37)

• Approximate nonparametric maximum likelihood for mixture models: a convex optimization approach to fitting arbitrary multivariate mixing distributions
• Credit portfolios, credibility theory, and dynamic empirical Bayes
• A survey of nonparametric mixing density estimation via the predictive recursion algorithm
• Empirical estimates for heteroscedastic hierarchical dynamic normal models
• On general maximum likelihood empirical Bayes estimation of heteroscedastic IID normal means
• Statistical theory powering data science
• Bayesball: A Bayesian hierarchical model for evaluating fielding in major league baseball
• Nonparametric empirical Bayes and compound decision approaches to estimation of a high-dimensional vector of normal means
• SURE estimates under dependence and heteroscedasticity
• Online estimation of individual-level effects using streaming shrinkage factors
• Estimating the mean and variance of a high-dimensional normal distribution using a mixture prior
• Approximate repeated-measures shrinkage
• Semi-parametric Bayesian inference for multi-season baseball data
• Optimal shrinkage estimation of mean parameters in family of distributions with quadratic variance
• Nonparametric hierarchical Bayes analysis of binomial data via Bernstein polynomial priors
• On generalized geometric distributions and improved estimation of batting average in cricket
• Modelling the Evolution of Distributions: An Application to Major League Baseball
• Competing process hazard function models for player ratings in ice hockey
• A nonparametric empirical Bayes approach to adaptive minimax estimation
• Estimation with Selected Binomial Information or Do You Really Believe That Dave Winfield is Batting .471?
• scientific article; zbMATH DE number 1031815 (Why is no real title available?)
• On SURE estimates in hierarchical models assuming heteroscedasticity for both levels of a two-level normal hierarchical model
• scientific article; zbMATH DE number 775737 (Why is no real title available?)
• Group-linear empirical Bayes estimates for a heteroscedastic normal mean
• A general framework for empirical Bayes estimation in discrete linear exponential family
• Nuclear penalized multinomial regression with an application to predicting at bat outcomes in baseball
• Adaptive sparse estimation with side information
• Asymptotically optimal nonparametric empirical Bayes via predictive recursion
• Model-based estimation of baseball batting metrics
• Hierarchical Bayesian modeling of hitting performance in baseball
• On the performance of the new minimax shrinkage estimators for a normal mean vector
• Optimal empirical Bayes estimation for the Poisson model via minimum-distance methods
• Using penalized-distance likelihood functions to analyze high-dimensional sparse/non-sparse data
• Joint restricted empirical likelihood and its applications for high-dimensional datasets
• Empirical Bayes when estimation precision predicts parameters
• Interval estimation for messy observational data
• An empirical Bayes mixture method for effect size and false discovery rate estimation

This page was built for publication: In-season prediction of batting averages: a field test of empirical Bayes and Bayes methodol\-ogies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2482971)