My current research focuses on developing innovative statistical methodologies for complex, high-dimensional, and dependent data, with particular emphasis on Bayesian inference, statistical machine learning, spatio-temporal modeling, and official statistics. A central theme of my work is the development of flexible, scalable, and computationally efficient approaches that accommodate complex dependence structures while providing principled uncertainty quantification and interpretable inference. Increasingly, this research explores the intersection of hierarchical statistical modeling, modern machine learning, and emerging artificial intelligence technologies.
A significant component of my research involves advancing statistical methodology for survey inference, small area estimation, data integration, and privacy-preserving statistical analysis. These efforts are motivated by the challenges and opportunities presented by increasingly heterogeneous data sources, evolving computational paradigms, and the growing demand for reliable inference in high-dimensional and data-rich environments. Applications span government statistics, economics, and environmental and ecological sciences.
More broadly, my research seeks to bridge foundational statistical principles with emerging data-driven methodologies, leveraging advances in machine learning and computation to develop rigorous, scalable, and trustworthy approaches to statistical inference and scientific discovery.