Copula-Based Multistate Hazard Model: An Inferential Methodology for Innocence Project

• Activity Number: 286
• Type: Topic Contributed
• Date/Time: Tuesday, August 2, 2011 : 8:30 AM to 10:20 AM
• Sponsor: Business and Economic Statistics Section
• Author(s): Kobi Ako Abayomi*+ and Jessica Gabel and Otis Brian Jennings
• Companies: Georgia Tech and Georgia State University and Duke University
• Keywords: Discrete Multivariate Distributions ; Statistical Dependence ; Statistics in Law ; Statistical Classification ; Discrete Dependence ; Case-Control Methods

Abstract

In 2009, the work of Innocence Network member organizations led to the exoneration of 27 people in the United States. Since 1992, the Innocence Projects have helped over 250 wrongly convicted persons prove their innocence and gain freedom.

Unfortunately, these exonerations are likely a miniscule sample of the number of wrongly convicted persons. Recent research suggests that the number innocents languishing in prison may be greater than 28,500, in non-death penalty cases alone. Many of these cases slip through the cracks: DNA evidence is unavailable, non-existent or insufficient to merit review for exoneration.

We suggest methodology for the possible determinants of exoneration using a case-control setup for discrete multivariate dependent data; the raw data the Innocence Projects gather - court records, criminal histories, personal and local demographics.