Welcome

I am an Assistant Professor in the Department of Political Science at Columbia University. I specialize in political methodology and develop statistical methods for questions in political science and the social sciences.

I am broadly interested in causal inference and machine learning methods for the social sciences. My research projects include external validity of causal findings and causal inference with network and spatial data. Please see Research for the overview of my research areas. My work has appeared or is forthcoming in various academic journals, such as American Political Science Review, American Journal of Political Science, Political Analysis, Journal of the American Statistical Association, Journal of the Royal Statistical Society (Series B), Neurips, and Science Advances.

I have won several awards for my research. In 2022, my paper on causal peer effects won the Best Conference Paper Award from Political Networks Section in APSA. In 2019, my work on causal diffusion analysis won the Gosnell Prize from the Society for Political Methodology. In 2017, I also received the John T. Williams Dissertation Prize.

I received a Ph.D. from Princeton University (2020) and a B.A. from the University of Tokyo (2015). I was a pre-doctoral fellow in the Department of Government at Harvard University from 2018 to 2020. I also studied at the University of Michigan, Ann Arbor, as a visiting student in 2013.

Representative Papers

1. External Validity and Generalization

• "Elements of External Validity: Framework, Design, and Analysis."
  American Political Science Review (2023).

• "Designing Multi-Site Studies for External Validity: Site Selection via Synthetic Purposive Sampling."
  Working Paper (2023).
  

2. Network Causal Inference (Causal Inference with Interference)

• "Identification and Estimation of Causal Peer Effects Using Double Negative Controls for Unmeasured Network Confounding."
  Journal of the Royal Statistical Society: Series B (Forthcoming).
  

• "Spillover Effects in the Presence of Unobserved Networks."
  Political Analysis (2021).

3. Machine Learning/Large Language Models for the Social Sciences

• "Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models."
  NeurIPS (2023).
  

• "Causal Interaction in Factorial Experiments: Application to Conjoint Analysis."
  Journal of the American Statistical Association (2019).
  

Recent Invited Talks

• In December 2023, I gave talks at Waseda University and University of Tokyo about external validity.
• In July 2023, I gave talks at PolMeth about my paper on multi-site studies for external validity and my paper on large language models.
• In May 2023, I gave a talk at MIT about external validity.
• In April 2023, I gave a talk at Harvard about external validity.
• In March 2023, I gave a talk at the University of Tokyo about my paper on causal inference with texts.
• In February 2023, I gave a talk at the University of North Carolina at Chapel Hill about my paper on external robustness.
• In October 2022, I gave a talk at the Quantitative Methods in the Social Sciences Program at Columbia University about my paper on external robustness.
• In October 2022, I gave a talk at the INFORMS Annual Meeting about my paper on causal peer effects.
• In April 2022, I gave a talk at Stanford about a new paper on external robustness.
• In March 2022, I gave a talk at the Department of Economics in Columbia about my paper on causal peer effects.
• In February 2022, I gave a talk at Yale about my paper on causal peer effects.