Statistical Analysis in Forensic Science: Evidential Values of Multivariate Physicochemical Data

Appendix F

Introduction to calcuLatoR software

F.1 Introduction

A graphical user interface called calcuLatoR for the calculation of likelihood ratios for univariate data (such as refractive index data; Section 1.2.2) in comparison problems has been developed and described in Zadora and Surma (2010). The LR model assumes two sources of variation: between replicates within the same object (within-object variability) and between replicates between various objects (between-object variability). It was assumed that the within-object distribution is normal with constant variance (equation (3.3)). The between-object distribution was modelled by a univariate kernel density estimation (equations (4.7) and (4.8)).

The calcuLatoR can also be used for evaluating the evidential value of multivariate data, but it must be assumed that the variables concerned are independent. In this situation, LR should be calculated for each variable separately and the final LR value is equal to their product.

F.2 Manual

Using the data files included in the starting package should return the same result for anyone using this software (Section 4.4.4). Therefore, these files can be used to check the accuracy of the software’s performance before an LR calculation is performed in real casework.

The starting package for Windows and Linux users is available in the relevant file folder named Appendix F on the website1. During the first execution, for example using calcuLatoR.exe for Windows users, an LR icon (Figure ...