Summary
Yajuan Si is a Research Associate Professor at the University of Michigan with nine years of post-PhD experience developing advanced Bayesian methods for latent variable models, complex survey inference, missing data, causal inference, and data confidentiality. Her work spans academia and applied research, from postdoctoral and faculty roles at Columbia, Wisconsin–Madison, and Michigan to earlier methodological projects at Duke and ETS focused on large-scale survey imputation. She combines deep theoretical expertise with practical solutions for high-dimensional categorical imputation and disclosure-risk reduction, often leveraging nonparametric Bayesian tools like Dirichlet process mixtures. Based in Ann Arbor, she brings a global training background (Duke, Hong Kong, Renmin University) and a track record of translating cutting-edge methodology into tools that address real-world survey and privacy challenges.
9 years of coding experience
12 years of employment as a software developer
PhD, Statistics, PhD, Statistics at Duke University
The University of Hong Kong (HKU)
BE, Statistics (minor on Actuarial Science), BE, Statistics (minor on Actuarial Science) at Renmin University of China
Chinese, English