Kwonsang Lee

Associate Professor
kwonsanglee (at) snu (dot) ac (dot) kr

I am an Associate Professor of Statistics at Seoul National University, where I lead the SNU Causal Inference Lab.

My research develops design- and algorithm-centric methods for causal inference, with a focus on matching, weighting, diagnostics, and randomization-based inference.

More about my research →

Portrait of Kwonsang Lee

Education

  • 2017–2020

    Postdoctoral Fellow, Department of Biostatistics, Harvard T.H. Chan School of Public Health

    advised by Francesca Dominici

  • 2012–2017

    Ph.D., Applied Mathematics and Computational Science (AMCS), University of Pennsylvania

    advised by Dylan Small

  • 2015–2016

    M.A., Statistics, University of Pennsylvania

  • 2006–2010

    B.S., Mathematics and Economics, Seoul National University

  • Aug 28

    Suehyun and Sangyong graduated with master’s degrees. Suehyun will begin her Ph.D. studies at Stanford University, and Sangyong will continue his research with our lab. Congratulations to both on their next steps!

  • Aug 19

    Our group held the 2026 Summer Lab Workshop! We were also happy to welcome our former lab member, Suhwan, who joined us for a short talk. Kwonsang gave a tutorial to our new master’s student and the undergraduate lab interns, and everyone shared updates on their research projects and future plans.

  • Aug 13

    We were delighted to host José R. Zubizarreta (Harvard Medical School and Harvard T.H. Chan School of Public Health) during his visit to SNU. He also gave a seminar titled Space-Time-Meta Causal Inference: A Weighting Perspective.

  • Aug

    We welcome Muhammad Qasim (Lund University) as a vising scholar in our lab from August 2026 to January 2027.

  • Jul

    We hosted Roberto Faleh (University of Tübingen) and Xiang Meng (Dana-Farber Cancer Institute and Harvard T.H. Chan School of Public Health) as visiting scholars in our lab. Roberto and Xiang gave talks titled Learning How Treatments Work: Causal Mediation When Sequential Ignorability Fails, and Reuse-Aware Inference for Matching Estimators: Central Limits and Single-Matching Variance Estimation, respectively.