Different Paradigms of Interpretation for Forensic Value of Evidence Quantification

• Activity Number: 339 - Model-Fitting, Likelihood-Based Inference, and Their Applications
• Type: Contributed
• Date/Time: Tuesday, August 1, 2017 : 10:30 AM to 12:20 PM
• Sponsor: IMS
• Author(s): Danica Ommen* and Christopher Saunders and Reinoud Stoel and Peter Vergeer
• Companies: South Dakota State University and South Dakota State University and Netherlands Forensic Institute and Netherlands Forensic Institute
• Keywords: forensic science ; statistical paradigms ; quantifying evidence ; Bayesian ; Frequentist ; Likelihood

Abstract

Currently, one of the major problems in the forensic science community is the confusion between different statistical paradigms. A quantification of the value of evidence is interpreted differently under each paradigm, and may even be the answer to different questions. It is our opinion that these issues need to be addressed before quantitative forensic analyses are considered a reliable science in the justice system. A related issue is the blending of paradigms that so often occurs during the statistical analysis for forensic evidence. Many statisticians will use techniques that are a combination of methods from different paradigms. When this occurs, there is often an issue of interpreting and successfully applying a result that is somewhere on the spectrum between paradigms. This presentation will focus on three different paradigms of evidence interpretation, the Bayesian, the Frequentist, and the Likelihoodist. The appropriate methods for quantifying the value of evidence under each paradigm and the corresponding interpretation of the result will be discussed. The presentation will conclude with some guidelines of how to "safely" mix the paradigms.