The National Science Foundation Division of Mathematical Sciences awarded a $110,000 Project Grant to the University of Florida Division of Sponsored Research under the Mathematical and Physical Sciences federal grant program (CFDA 47.049). The three-year award will support the development of novel modeling and Bayesian analysis methods for high-dimensional time series data.
Specifically, the principal investigators will create a framework to represent multi-dimensional time series data as a linear combination of independent, one-dimensional latent time series processes. This representation will explain the evolution of the data over time and intrinsic relationships between variables. It will also facilitate more accurate, efficiently computable predictions by incorporating information across components and time periods. The investigators plan to develop free software packages to disseminate the results and support young researchers through graduate training opportunities.
Generated 1/7/24, 12:16 AM