Congratulations to Statistics PhD candidate Sarah Tan, who has been named the recipient of the American Statistical Association's 2017 Wray Jackson Smith Scholarship.
Kevin Konty, a member of the scholarship committee, writes: For her dissertation, Tan is developing methods for causal inference using observational data, including new balancing scores based on tree ensembles for complicated treatment selection processes, and ways to incorporate the uncertainty of the treatment selection model into the outcome model. She will work with the NYC Office of School Health to apply these methods to the potential effects of later school start times. Tan plans to use the Wray Jackson Smith Scholarship to support this project, including transportation costs to New York City and future conferences.
Tan’s interests lie at the intersection of statistics and machine learning. She is particularly interested in public policy applications, especially government statistics where causal inference is needed for impact evaluation and policy planning. She is also interested in how government data from various scales—federal, local, and across agencies—can be synthesized to obtain better estimates Tan has worked on several research projects with New York City (NYC) agencies, including implementing a Bayesian evidence synthesis framework to estimate hepatitis prevalence. This effort brought together information from a variety of sources that had been analyzed separately. Tan has also worked with the NYC Health and Hospitals Corporation, analyzing hospital readmissions and providing feedback to hospital administrators.
Tan graduated with a bachelor’s degree in statistics and economics from the University of California, Berkeley, and a master’s degree in statistics from Columbia University. She is a fourth-year PhD student in statistics at Cornell University. She was also a 2014 Data Science for Social Good Fellow and has spent summers at Xerox Research and Microsoft Research.