Short-Run Demand and Uncertainty of Outcome in Major League Baseball

This article explores the importance of uncertainty in athletic contests. We use a probit model and Monte Carlo simulations to forecast game outcomes in Major League Baseball. Simulations are necessary to understand fully the preferences that consumers have towards uncertainty in sports. We use these simulations to estimate demand using attendance data for regular season games. Our findings show that when game, playoff, and consecutive season uncertainty measures are all included in estimating attendance for individual games, only the metrics that are related to the home team's standing are significant. These metrics include the change in performance from the previous season and the importance of the game in qualifying for the playoffs.