Avoiding overstating the strength of forensic evidence: Shrunk likelihood ratios/Bayes factors


When strength of forensic evidence is quantified using sample data and statistical models, a concern may be raised as to whether the output of a model overestimates the strength of evidence. This is particularly the case when the amount of sample data is small, and hence sampling variability is high. This concern is related to concern about precision. This paper describes, explores, and tests three procedures which shrink the value of the likelihood ratio or Bayes factor toward the neutral value of one. The procedures are: (1) a Bayesian procedure with uninformative priors, (2) use of empirical lower and upper bounds (ELUB), and (3) a novel form of regularized logistic regression. As a benchmark, they are compared with linear discriminant analysis, and in some instances with non-regularized logistic regression. The behaviours of the procedures are explored using Monte Carlo simulated data, and tested on real data from comparisons of voice recordings, face images, and glass fragments.

Publication DOI: https://doi.org/10.1016/j.scijus.2017.12.005
Divisions: College of Engineering & Physical Sciences
College of Business and Social Sciences > Aston Institute for Forensic Linguistics
?? 53981500Jl ??
College of Business and Social Sciences > School of Social Sciences & Humanities
Additional Information: © 2018 The Authors. Published by Elsevier B.V. on behalf of The Chartered Society of Forensic Sciences. This is an open access article under the CC BY license (http://creativecommons.org/licenses/BY/4.0/). Funding: Simons Foundation Visiting Fellowship, EPSRC Grant Number EP/K032208/1
Uncontrolled Keywords: Likelihood ratio,Bayes factor,Shrinkage,Conservative,Regularize,Logistic regression
Publication ISSN: 1355-0306
Last Modified: 06 May 2024 07:22
Date Deposited: 02 Jan 2018 10:45
Full Text Link:
Related URLs: http://linkingh ... 355030617301582 (Publisher URL)
PURE Output Type: Article
Published Date: 2017-12-22
Published Online Date: 2017-12-22
Accepted Date: 2017-12-20
Authors: Morrison, Geoffrey Stewart (ORCID Profile 0000-0001-8608-8207)
Poh, Norman



Version: Published Version

License: Creative Commons Attribution

| Preview

Export / Share Citation


Additional statistics for this record