Calculation of forensic likelihood ratios: Use of Monte Carlo simulations to compare the output of score-based approaches with true likelihood-ratio values

TL;DR

This paper evaluates various score-based methods for calculating forensic likelihood ratios using Monte Carlo simulations, highlighting the importance of considering both similarity and typicality for accurate forensic interpretation.

Contribution

It introduces a simulation-based framework to compare score-based likelihood ratio methods against true values, emphasizing the need to incorporate both similarity and typicality.

Findings

Similarity-only scores are inadequate for forensic likelihood ratios.

Methods accounting for both similarity and typicality outperform others.

Monte Carlo simulations effectively validate likelihood ratio approaches.

Abstract

A group of approaches for calculating forensic likelihood ratios first calculates scores which quantify the degree of difference or the degree of similarity between pairs of samples, then converts those scores to likelihood ratios. In order for a score-based approach to produce a forensically interpretable likelihood ratio, however, in addition to accounting for the similarity of the questioned sample with respect to the known sample, it must also account for the typicality of the questioned sample with respect to the relevant population. The present paper explores a number of score-based approaches using different types of scores and different procedures for converting scores to likelihood ratios. Monte Carlo simulations are used to compare the output of these approaches to true likelihood-ratio values calculated on the basis of the distribution specified for a simulated population. The inadequacy of approaches based on similarity-only or difference-only scores is illustrated, and the relative performance of different approaches which take account of both similarity and typicality is assessed.