Online Program Home
  My Program Register Now!

Abstract Details

Activity Number: 6 - Advocating, Implementing and Explaining Bayesian Analyses in Statistical Consultations
Type: Invited
Date/Time: Sunday, July 28, 2019 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistical Consulting
Abstract #300092
Title: The Jury is Out: Communicating Bayesian Statistics in a Courtroom Trial
Author(s): Mark Glickman*
Companies: Harvard University
Keywords: risk assessment; Poisson process; sports; baseball; injury; law
Abstract:

Explaining the details of a Bayesian analysis effectively to non-statistician colleagues or consulting clients is difficult enough, but try explaining Bayesian analyses to a trial jury. In this talk, I describe a case tried in Massachusetts Superior Court in which I was retained as a testifying expert. The case involved a woman suing the Red Sox organization for negligence as a result of her being struck and seriously injured by a foul ball. I was asked by the defendant to estimate the risk of being injured by a foul ball in the section of Fenway Park where the plaintiff was injured. My risk calculation assumed that injury occurrences within baseball games and over the course of a baseball season could be modeled as a Poisson process. Data for my analyses were provided by the Red Sox. Inferences for the probability of injury were determined through a Bayesian analysis, resulting in asymmetric credible intervals. I relate the process of describing the Bayesian analysis to the defense lawyer prior to the trial, and how the use of visual aids helped communicate essential ideas underlying the Bayesian approach so that the jury could appreciate the analysis of risk assessment.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program