Thesis - Open Access
Master of Science (MS)
Mathematics and Statistics
Christopher P. Saunders
Forensic Science, Handwriting, Sufficiency Studies, U-Processes, U-Statistics
One of the main metrics for deciding if a given forensic modality is useful across a broad spectrum of cases, within a given population, is the Random Match Probability (RMP), or the corresponding discriminating power. Traditionally, the RMP of a given modality is studied by comparing full `templates' and estimating the rate at which pairs of templates 'match' in a given population. This strategy leads to a natural U-statistic of degree two. However, in questioned document examination, the RMP is studied as a function of the amount of handwriting contained in the two documents being compared; turning the U-statistic into a U-process. This work is focused on providing background on forensic sufficiency studies, RMP, and the U-processes that naturally arise in this class of problems.
Library of Congress Subject Headings
Writing -- Identification.
Includes bibliographical references (pages 64-67)
Number of Pages
South Dakota State University
In Copyright - Educational Use Permitted
Fuglsby, Cami, "U-Statistics for Characterizing Forensic Sufficiency Studies" (2017). Electronic Theses and Dissertations. 1715.