Project Grant 2210337

This three-year Project Grant from the National Science Foundation's Division of Mathematical Sciences, under the Mathematical and Physical Sciences federal grant program (CFDA 47.049), provides $320,000 to the University of North Carolina at Chapel Hill to conduct collaborative research on emerging variants of generalized fiducial inference. The research aims to explore the evolution of the fiducial argument as a response to modern data science questions and techniques. Researchers will develop easy-to-implement algorithms to sample from generalized fiducial distributions, improving the practical applicability of generalized fiducial inference. They will also investigate fundamental issues of generalized fiducial inference as applied to manifolds and lay the groundwork to make it applicable to non-parametric problems. As an important application, the project will develop post-hoc calibration of the strength of evidence in forensic science. Graduate students, including those from underrepresented groups, will receive training through research involvement. Results are expected to expand the understanding of statistics and data science foundations.