Validation of Likelihood Ratio Methods Used for Forensic Evidence Evaluation: Application in Forensic Fingerprints

Rudolf Haraksim

    Research output: ThesisPhD Thesis - Research UT, graduation UT

    670 Downloads (Pure)


    In this chapter the Likelihood Ratio (LR) inference model will be introduced, the theoretical aspects of probabilities will be discussed and the validation framework for LR methods used for forensic evidence evaluation will be presented. Prior to introducing the validation framework, following questions will be addressed: “which aspects of a forensic evaluation scenario need to be validated?‿, “what is the role of the LR as part of a decision process?‿ and “how to deal with uncertainty in the LR calculation?‿ The answers to these questions are necessary to define the validation strategy based on the validation criteria. The questions: “what to validate?‿ focusing on defining validation criteria and methods, and “how to validate?‿ dealing with the implementation of a validation protocol, form the core of this chapter. The validation framework described can be used to provide assistance to the forensic practitioners, when determining the suitability and applicability of the LR method developed in the forensic practice by introducing performance characteristics, performance metrics, validation criteria and the decision thresholds. This chapter will start with the introduction of the LR inference model, followed by the validation framework proposed.
    Original languageUndefined
    Awarding Institution
    • University of Twente
    • Meuwly, Didier, Supervisor
    • Veldhuis, Raymond, Supervisor
    • Meuwly, Didier, Supervisor
    Thesis sponsors
    Award date18 Jun 2014
    Place of PublicationEnschede
    Print ISBNs978-90-365-3648-6
    Publication statusPublished - 18 Jun 2014


    • IR-91812
    • EWI-25056
    • EC Grant Agreement nr.: FP7-PEOPLE-ITN-2008
    • Validation
    • SCS-Safety
    • METIS-305078
    • Fingerprints
    • Forensic Evidence Evaluation
    • Ratio Methods

    Cite this