Abstract:
|
In Forensic Science one of the main metrics for deciding if a given forensic modality is appropriate for use in a judicial setting is the Random Match Probability (RMP). Traditionally, RMP's are studied by comparing two 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 and a corresponding U-statistic of degree 4 to estimate the standard error. In questioned document examination there have been recent movements to study the RMP as a function of the amount of handwriting in the two handwritten documents being compared, which turns the U-statistics into U-processes. This work is focused on providing background on forensic sufficiency studies, RMP, and the U-processes that naturally arise in this class of problems.
|