We develop and apply causal inference methods that integrate randomized trials and real-world data to generate rigorous, actionable evidence for clinical decision-making and public health.
Our research focuses on developing statistically rigorous and practically applicable methods for causal inference using complex health data. A central goal is to bridge randomized clinical trials and large-scale observational data—such as EHRs, registries, and claims—to enable principled generalization of evidence across populations and care settings. We address key challenges including treatment heterogeneity, partial compliance and adherence, missing data, and time-varying treatments. We collaborate closely with clinical and data science teams to apply statistical methods to high-impact problems. Current applications include substance use disorders (including OUD), Alzheimer’s disease and aging, stroke, and cancer.
Biography
Dr. Sun is an Assistant Professor in the Division of Biostatistics. Her research focuses on (i) developing rigorous and accessible methods for causal inference and (ii) applying them to support evidence-based public health and clinical decision-making. She integrates randomized trials and large-scale observational data to address complex real-world questions, with work spanning treatment heterogeneity, missing data, and time-varying treatments, and applications in substance use disorders, neurological diseases, and cancer. She received her PhD in Biostatistics from McGill University and her MS in Statistics from the University of Washington. Prior to joining Weill Cornell Medicine, she was a postdoctoral fellow at Harvard T.H. Chan School of Public Health and a research scientist at Massachusetts General Hospital.
