A Sequential Game Model of Sports Championship Series: Theory and Estimation

Using data from the championship series in three professional sports basketball baseball and hockey we estimate the parameters of a sequential game model for the best of n games championship series The unique subgame perfect equilibrium determines performance levels based on exogenous home eld advantage and abilities of the two players teams The model provides a robust computational framework for studying strategic incentives in any sports based on identical stages for example single elimination tournaments and individual tennis matches We control for measured and unobserved di erences in team strength and we improve the small sample properties of our estimates using a bootstrap on the maximum likelihood estimates We nd negligible strategic e ects in all three sports teams in each sport play as well as possible in each game regardless of the games importance in the series We also estimate negligible unobserved heterogeneity after controlling for regular season records and past appearance in the championship series teams are estimated to be exactly as strong as they appear on pape