Bayesian estimation of in-game home team win probability for college basketball

Abstract Two new Bayesian methods for estimating and predicting in-game home team win probabilities in Division I NCAA men’s college basketball are proposed. The first method has a prior that adjusts as function of lead differential time elapsed. second is an adjusted version the first, where adjustment linear combination estimator with time-weighted pregame probability. proposed compared to existing methods, showing competitive or outperform both estimation prediction. utility illustrated via application 2012/2013 through 2019/2020 Men’s Basketball seasons.