Sep 2024,
Revise & Resubmit,
Journal of American Statistical Association
Most work on treatment choice and policy learning focuses on utilitarian welfare (i.e., average welfare), which can be sensitive to skewed heterogeneity. We propose a robust policy learning framework that enables the policymaker to act with prudence/negligence and to be influenced by vote shares.


Shapes as Product Differentiation︎︎︎
with Eric Schulman, Kristen Grauman, Santhosh Ramakrishnan
arxiv︎︎︎ slides︎︎︎
Nov 2022,
Revise & Resubmit,
RAND Journal of Economics
Many differentiated products have key attributes that are high-dimensional (e.g., design, text). We consider one of the simplest design products, fonts, and quantify their shapes by constructing neural network embeddings. Using the embeddings and data from the world's largest online market place for fonts, we study the causal effect of a merger on the merging firm's creative decisions of product differentiation.
*This project is featured in a typography magazine ︎︎︎ and included in the MIT graduate machine learning course ︎︎︎.


Feb 2025
The classic control function approach requires invertibility or point-identified controls, which limits its applicability (e.g., discrete treatments, controls as intervals). We allow the control function to be set-valued and derive sharp bounds on structural parameters.
Copyright and Competition: Estimating Supply and Demand with Unstructured Data︎︎︎
with Kyungho Lee
arxiv︎︎︎
Jan 2025
To understand the role of copyright policy in markets for products with visual attributes, we estimate a structural model of supply (e.g., product positioning) and demand (e.g., tastes for visual attributes) using image data. Visual similarity, calculated using neural network embeddings, serves as a crucial metric for the analysis.
Mar 2025
Finding IVs is a heuristic and creative process, and justifying exclusion restrictions is largely rhetorical. We propose using large language models (LLMs) to systematically search for new IVs through narratives and counterfactual reasoning.
Estimating Causal Effects of Discrete and Continuous Treatments with Binary Instruments︎︎︎
with Victor Chernozhukov, Iván Fernández-Val, Kaspar Wüthrich
arxiv︎︎︎
Dec 2024
We identify average and quantile treatment effects for binary, ordered and continuous treatments with only binary IV under local copula invariance. The resulting semiparametric estimation procedures are very easy to implement.
Inference for Interval-Identified Parameters Selected from an Estimated Set︎︎︎
with Adam McCloskey
arxiv︎︎︎
Mar 2025
We develop new inference tools for interval-identified welfare at a policy chosen from an estimated set (e.g., an estimated identified set).
On Quantile Treatment Effects, Rank Similarity, and the Variation of IVs︎︎︎
with Haiqing Xu
arxiv︎︎︎ slides︎︎︎
Aug 2023
We provide a novel interpretation for rank similarity, which motivates us to relax it in a way that is useful to bound the QTEs using multi-valued IVs. The bounds are easy to calculate in practice and are shown to be informative.
Semiparametric Models for Dynamic Treatment Effects and Mediation Analyses with Observational Data︎︎︎
with Sungwon Lee
slides︎︎︎
Aug 2023
We propose a class of semiparametric models using copula to point identify and efficiently estimate dynamic treatment effects and dynamic mediator effects under treatment endogeneity.
Feb 2024
We develop a test of information ordering to examine if the true information structure is at least as informative as a proposed baseline. We utilize the notion of Bayes Correlated Equilibrium (BCE).


Effects of New Good Entry in Complementarity Markets: The Case of Font Market
with Matt Shum
in progress
A Computational Approach to Identification of Treatment Effects for Policy Evaluation︎︎︎
with Shenshen Yang
arxiv︎︎︎ matlab codes︎︎︎
2024
Journal of Econometrics
Vol. 240, 105680
We propose a computational framework to calculate sharp nonparametric bounds (using binary IV that satisfies full independence) on various policy-relevant treatment parameters that are defined as weighted averages of the MTE.


Optimal Dynamic Treatment Regimes and Partial Welfare Ordering︎︎︎
supplement︎︎︎ matlab codes & data︎︎︎ working paper︎︎︎ slides︎︎︎
2023
Journal of American Statistical Association
Vol. 119, pp. 2000-2010
*Editor’s Choice 2023
We partially identify the optimal dynamic regime from observational data, relaxing sequential randomization but instead using IVs. As a first step, we establish the sharp partial ordering of welfares, which summarizes the signs of dynamic treatment effects.


2023
Journal of Econometrics
Vol. 234, pp. 732-757
Treatments are determined by strategic interaction, which poses interesting identification problems.


2021
Journal of American Statistical Association
Vol. 116, pp. 192-195
I discuss identification of optimal treatment rules under treatment endogeneity and propose a novel identifying condition.
2021
Journal of Econometrics
Vol. 225, pp. 132-147
Time-varying treatment effects are considered in a nonparametric model with treatment endogeneity.
Nonparametric Estimation of Triangular Simultaneous Equations Models under Weak Identification︎︎︎
supplement︎︎︎ matlab codes & data︎︎︎
2020
Quantitative Economics
Vol. 11, pp. 161-202
Using a control function approach, weak instruments are characterized as a concurvity problem.
Estimation and Inference with a (Nearly) Singular Jacobian︎︎︎
with Adam McCloskey
supplement︎︎︎ matlab codes & data︎︎︎2019
Quantitative Economics
Vol. 10, pp. 1019-1068
In a set of nonlinear models, we propose reparametrization that facilitates robust inference under weak identification.
Estimation in a Generalization of Bivariate Probit Models with Dummy Endogenous Regressors︎︎︎
with Sungwon Lee
supplement︎︎︎ matlab codes & data︎︎︎