Probabilistic Evaluation of Handwriting Evidence: Likelihood Ratio for Authorship

Abstract

The evaluation of handwritten characters that are selected from an anonymous letter and written material from a suspect is an open problem in forensic science. The individualization of handwriting is largely dependent on examiners who evaluate the characteristics in a qualitative and subjective way. Precise individual characterization of the shape of handwritten characters is possible through Fourier analysis: each handwritten character can be described through a set of variables such as the surface and harmonics as demonstrated by Marquis and co-workers in 2005. The assessment of the value of the evidence is performed through the derivation of a likelihood ratio for multivariate data. The methodology allows the forensic scientist to take into account the correlation between variables, and the non-constant variability within sources (i.e. individuals). Numerical procedures are implemented to handle the complexity and to compute the marginal likelihood under competing propositions. Copyright (c) 2008 Royal Statistical Society.

Score-based likelihood ratios for handwriting evidence

“…Due to these points of subjectivity, SLR values must be interpreted with far more caution than the LR based on a welldefined and known probability model (e.g., simple one-contributor DNA LRs). 9 Some conclusions could be drawn from the various results presented above as to the best SLR technique to use; however, the authors resist as varying any of the subjective factors enumerated above may affect the outcome. Also, innovative score-based approaches have appeared in the literature since this work was undertaken that also should receive consideration [18].…”

“…The authors are simply cautioning against reporting RMEP and RMED as the ''error rate'' for any likelihood ratio method and illustrating a more meaningful alternative. 9 Often when calculating a LR, the probability distribution is unknown and must be estimated. In these cases, this estimation process induces subjectivity, just as when estimating the SLR.…”

Oval in males and triangular in females? A quantitative evaluation of sexual dimorphism in the human obturator foramen

“…Only a precise quantitative approach such as Fourier analysis allows for unambiguous characterization and statistical analysis. The assignation of sex to a hipbone of a single individual of unknown sex, which is of evident practical interest, cannot be simply resolved as Fourier descriptors are used, and will require further specific probabilistic approaches (see, e.g., Bozza et al, 2008). Further investigations would also be interesting to focus on the status of the non-significant sexually dimorphic shapes, to study this trait during growth, to investigate correlations with other sexual dimorphic traits of the pelvis, and to explore this trait in the populations of various geographic origins.…”

Different likelihood ratio approaches to evaluate the strength of evidence of MDMA tablet comparisons

“…For reasons of simplicity in this paper variances that are assumed known but may vary from batch to batch are used. In future research priors on variances will be used [27]. Detailed information about LR formulas with kernel density estimates and other extensions can be found in related work [20].…”