Project Grant 2610432

Federal Grant Award Summary

The National Science Foundation's Division of Mathematical Sciences awarded $199,065 to the Regents of the University of California at Riverside under the Mathematical and Physical Sciences program (CFDA 47.049) for a three-year project spanning July 1, 2026, through June 30, 2029. This project grant funds the development of advanced statistical methodologies for causal inference and treatment-effect estimation in observational data analysis. The research delivers new methods for analyzing multi-level and continuous interventions—such as medication dosages and program participation intensity—by combining stabilized weighting techniques, empirical likelihood approaches, and deep learning representations to overcome limitations in traditional propensity score methods that often produce unstable or unreliable results when applied to high-dimensional data.

The project's primary deliverables include novel methodological frameworks for counterfactual distribution estimation, dose-response analysis, and general loss-based causal inference that enhance the stability and accuracy of treatment-effect estimation beyond binary interventions. Applications of these research products span public health, healthcare delivery, social policy programs, and digital health, enabling more credible evidence-based decision-making from large-scale datasets. Additionally, the grant supports workforce development through graduate and undergraduate student training, interdisciplinary collaboration, and outreach activities designed to broaden participation in data science and statistics fields.