Handwriting analysis is conducted through the expertise of Forensic Document Examiners (FDEs) by visually comparing writing samples. Through their training and years of experience, FDEs are able to recognize critical characteristics of writing to evaluate the evidence of writership. In recent years, there have been incentives to further investigate how to quantify the similarity between two written documents to support the conclusions drawn by FDEs. One way to extract information from these documents is to define various features within handwritten samples. Using an automatic algorithm within the ‘handwriter’ package in R, a sample can split into “graphs”, which are small units of writing. These graphs are sorted into 40 exemplar groups or “clusters”. The clusters consist of graphs that have similar structures found in documents throughout a database with many writers. The number of graphs per cluster for each document written by a given person acts as a quantitative feature of the handwriting. This project aims to use experimental data collected at CSAFE to study how to assess source-level hypotheses and obtain “weight-of-evidence” summaries to support examiner conclusions. Specifically, statistical models can be used to compute Bayes factors, likelihood ratios, and four different types of score-based likelihood ratios. Common source score-based likelihood ratios are explored, along with trace-anchored, source-anchored, or general-match specific source varieties, using machine learning algorithms with high discriminating capabilities.
Statistical support for weight of evidence determinations of handwriting evidence

Conference/Workshop:
European Network of Forensic Handwriting Experts (ENFHEX) Conference and Business Meeting
European Network of Forensic Handwriting Experts (ENFHEX) Conference and Business Meeting
Published: 2021
Primary Author: Danica Ommen
Secondary Authors: Madeline Johnson
Type: Presentation Slides
Related Resources
Significance of image brightness levels for PRNU camera identification
A forensic investigator performing source identification on a questioned image from a crime aims to identify the unknown camera that acquired the image. On the camera sensor, minute spatial variations…
Methodological problems in every black-box study of forensic firearm comparisons
Reviews conducted by the National Academy of Sciences (2009) and the President’s Council of Advisors on Science and Technology (2016) concluded that the field of forensic firearm comparisons has not…
First impressions matter: Mundane obstacles to a forensic device for probabilistic reporting in fingerprint analysis
This article investigates why statistical reasoning has had little impact on the practice of friction ridge (or ‘fingerprint’) examination, despite both interest and some modest scientific progress toward this goal.…
How signature complexity affects expert and lay ability to distinguish genuine, disguised and simulated signatures
This study examined how variations in signature complexity affected the ability of forensic document examiners (FDEs) and laypeople to determine whether signatures are authentic or simulated (forged), as well as…