Tutorial on logistic-regression calibration and fusion:converting a score to a likelihood ratio

@article{Morrison2013TutorialOL,
  title={Tutorial on logistic-regression calibration and fusion:converting a score to a likelihood ratio},
  author={Geoffrey Stewart Morrison},
  journal={Australian Journal of Forensic Sciences},
  year={2013},
  volume={45},
  pages={173 - 197}
}
  • G. Morrison
  • Published 7 May 2013
  • Computer Science
  • Australian Journal of Forensic Sciences
Logistic-regression calibration and fusion are potential steps in the calculation of forensic likelihood ratios. The present paper provides a tutorial on logistic-regression calibration and fusion at a practical conceptual level with minimal mathematical complexity. A score is log-likelihood-ratio like in that it indicates the degree of similarity of a pair of samples while taking into consideration their typicality with respect to a model of the relevant population. A higher-valued score… 
Research Report CALCULATION OF FORENSIC LIKELIHOOD RATIOS: USE OF MONTE CARLO SIMULATIONS TO COMPARE THE OUTPUT OF SCORE- BASED APPROACHES WITH TRUE LIKELIHOOD-RATIO VALUES
TLDR
The present paper explores a number of score-based approaches using different types of scores and different procedures for converting scores to likelihood ratios, and compares the output of these approaches to true likelihood-ratio values calculated on the basis of the distribution specified for a simulated population.
Sampling variability in forensic likelihood-ratio computation: A simulation study.
Calculating likelihood ratios for forensic speaker comparisons using phonetic and linguistic parameters
The research presented in this thesis examines the calculation of numerical likelihood ratios using phonetic and linguistic parameters derived from a corpus of recordings of speakers of Southern
Statistical Models in Forensic Voice Comparison
TLDR
The aim of the chapter is to bridge the gap between general introductions to forensic voice comparison and the highly technical automatic-speaker-recognition literature from which the signal-processing and statistical-modeling techniques are mostly drawn.
Biometric evidence evaluation: an empirical assessment of the effect of different training data
TLDR
Two likelihood ratio values which differ in the nature of training scores they use and therefore consider slightly different interpretations of the two hypotheses are observed in the context of evidence evaluation from a face, a fingerprint and a speaker recognition system.
The Influence of Background Data Size on the Performance of a Score-based Likelihood Ratio System: A Case of Forensic Text Comparison
TLDR
This study investigates the robustness and stability of a likelihood ratio–based (LR-based) forensic text comparison (FTC) system against the size of background population data and indicated that the score-based approach is more robust against data scarcity than the feature- based approach.
Language and the Law Where the science ends and the law begins : likelihood ratio-based forensic voice comparison in a $ 150 million telephone fraud 1
The first use of likelihood ratios for the evaluation of forensic voice comparison evidence in a real trial in Australia is documented. Important steps in the process of estimating the strength of
...
...

References

SHOWING 1-10 OF 51 REFERENCES
An Issue in the Calculation of Logistic-Regression Calibration and Fusion Weights for Forensic Voice Comparison
TLDR
Two procedures for calibration and fusion of likelihood ratios in forensic voice comparison and automatic speaker recognition are compared, one using pooled data and the other using mean values from each speaker-comparison pair.
Estimating the Precision of the Likelihood-Ratio Output of a Forensic-Voice-Comparison System
TLDR
Two procedures for estimating the precision of the output of a forensic-comparison system, a non-parametric estimate and a parametric estimate of its 95% credible interval are described.
Likelihood-ratio forensic voice comparison using parametric representations of the formant trajectories of diphthongs.
  • G. Morrison
  • Mathematics
    The Journal of the Acoustical Society of America
  • 2009
TLDR
The cross-validated likelihood ratios from the best-performing system for each vowel phoneme were fused using logistic regression and the resulting fused system had a very low error rate, thus meeting one of the requirements for admissibility in court.
Measuring, refining and calibrating speaker and language information extracted from speech
TLDR
A new methodology, based on proper scoring rules, is proposed, allowing for the evaluation of the goodness of pattern recognizers with probabilistic outputs, which are intended to be usefully applied over a wide range of applications, having variable priors and costs.
Automatic-type calibration of traditionally derived likelihood ratios: forensic analysis of australian English /o/ formant trajectories
TLDR
A traditional-style phonetic-acoustic forensic-speakerrecognition analysis was conducted on Australian English /o/ recordings, and calibration ameliorated some likelihood-ratio results which had offered strong support for a contrary-to-fact hypothesis.
Likelihood Ratio Calibration in a Transparent and Testable Forensic Speaker Recognition Framework
TLDR
Proposed application-independent evaluation techniques (Cllr and APE curves) are finally addressed as a proper way for presenting results of proficiency testing in courts, as these evaluation metrics clearly show the influence of calibration errors in the accuracy of the inferential decision process.
...
...