Abstract

https://ssrn.com/abstract=2363709
 


 



Optimal Stopping in the NBA: An Empirical Model of the Miami Heat


Mathew Goldman


UC San Diego

Justin M. Rao


Microsoft Research; Microsoft Corporation - Microsoft Research - Redmond

August 19, 2014


Abstract:     
We study how highly experienced agents, professional basketball players, solve an optimal stopping problem. By rule, teams must shoot within 24 seconds of the start of a possession. The decision of when to shoot requires weighing the current shooting opportunity against the continuation value of the possession. At each second of the "shot clock," optimal play requires that a lineup's reservation shot value equals the continuation value of the possession. We empirically test this prediction with a structural stopping model. Most lineups adopt a reservation threshold that matches the continuation value function very closely. These lineups tend to be those with more shared playing experience. Mistakes we do observe come in the form too low a threshold and excess steepness. Overall, the lineups we study capture 84% of the gains of a dynamic threshold vs. an optimal fixed threshold, with only a single lineup estimated to capture less than 66%.

Number of Pages in PDF File: 35

Keywords: optimal stopping, expertise, lab vs. field, behavioral biases, marginal thinking

JEL Classification: D83, C51, D03, D22


Open PDF in Browser Download This Paper

Date posted: December 6, 2013 ; Last revised: August 20, 2014

Suggested Citation

Goldman, Mathew and Rao, Justin M., Optimal Stopping in the NBA: An Empirical Model of the Miami Heat (August 19, 2014). Available at SSRN: https://ssrn.com/abstract=2363709 or http://dx.doi.org/10.2139/ssrn.2363709

Contact Information

Mathew Goldman
UC San Diego ( email )
CA
United States
Justin M. Rao (Contact Author)
Microsoft Research ( email )
641 Avenue of Americas
7th Floor
New York, NY 11249
United States
Microsoft Corporation - Microsoft Research - Redmond ( email )
Building 99
Redmond, WA
United States
Feedback to SSRN


Paper statistics
Abstract Views: 1,278
Downloads: 226
Download Rank: 107,000