This project leveraged the properties of kernel functions in developing a method that enables statistical support for the inference of the identity of source of sets of trace and control objects with a single test.
Forensic chemists are often criticized for the lack of quantitative support for the conclusions of their examinations. Although scholars advocate for the use of a Bayes factor to quantify the weight of forensic evidence, it is often impossible to assign the necessary probability measures to perform likelihood-based inference on chemical data. The method proposed in the current project is generic, since it can be easily tailored to any type of data encountered in forensic chemistry, and it does not depend on the dimension or the type of data analyzed. The application of this method to paint evidence analyzed by FTIR shows that this type of evidence has substantial probative value. Finally, the proposed approach can easily be extended to other types of chemical evidence, such as glass, fibers, and dust. (publisher abstract modified)
Downloads
Similar Publications
- Design of Light-Induced Solid-State Plasmonic Rulers via Tethering Photoswitchable Molecular Machines to Gold Nanostructures Displaying Angstrom Length Resolution
- FY 2024 Solicitation Overview: Edward Byrne Memorial Justice Assistance Grant (JAG) Program—Local Solicitation
- Technology Use Among the Nation’s Medical Examiner and Coroner Offices: Data from the 2018 Census of Medical Examiner and Coroner Offices