Research

My research lies at the intersection of statistics and machine learning, with a focus on developing rigorous statistical methodology and scalable computational tools for analyzing complex, high-dimensional, and imperfect data. Motivated by challenges in public health, biomedical research, and artificial intelligence, my work spans statistical theory, methodological innovation, and real-world applications, aiming to transform noisy and heterogeneous data into reliable scientific insights and informed decision-making. The projects below highlight the major directions of my research. Each project page includes an overview of the methodologies, related publications, and selected presentations. You can also browse my publications by year here and my presentations by year here.

Modeling Behavioral and Neuroimaging Dynamics

This work develops advanced statistical modeling techniques to build efficient and scalable computational frameworks for investigating decision-making dynamics in behavioral tasks and neuroimaging measures.

Integrative learning for Individualized Treatment Rules

This work introduces statistical methodologies for integrating data from clinical trials and and real-world data, which may share a common treatment arm but differ in their alternative treatment options, to learn robust and reliable individualized treatment rules.

Statistical Learning with Imperfect Data

This project develops a range of statistically principled methods for learning from missing, censored, and error-prone data, including boosting prediction, variable selection, joint longitudinal and time-to-event modeling.

Interdisciplinary Statistical Learning Applications

This work applies machine learning and statistical modeling to real-world prediction and inference problems across diverse domains, including social media influence, infrastructure reliability, pharmacological evaluation, and healthcare diagnostics. The studies identify key predictive and causal factors, incorporate uncertainty quantification, cost-aware decision-making, and robust missing-data handling, and systematically compare model performance across a range of methodological approaches.