Sep 2022,
R&R, Journal of American Statistical Association

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.

Apr 2022,

R&R, Journal of Econometrics

We propose a framework to systematically calculate sharp nonparametric bounds (using binary IV) on various policy-relevant treatment parameters that are defined as weighted averages of the MTE.

Shapes as Product Differentiation ︎︎︎

with Eric Schulman, Kristen Grauman, Santhosh Ramakrishnan

slides ︎︎︎

Nov 2022


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 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 by using the embeddings in a synthetic control method.

*This project is featured in a typography magazine ︎︎︎ and included in the MIT graduate machine learning course ︎︎︎.

On Quantile Treatment Effects, Rank Similarity, and Multiple IVs 

with Haiqing Xu

slides ︎︎︎

Oct 2022

New draft coming soon!

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 multiple IVs. The bounds are easy to calculate in practice and are shown to be informative.

Testing for Information Structure under Bayes Correlated Equilibrium

with Hiro Kaido, Lorenzo Magnolfi, Camilla Roncoroni

in progress

Oct 2020,
Journal of Econometrics,

Treatments are determined by strategic interaction, which poses interesting identification problems.

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.

Journal of Econometrics,
Vol. 225, pp. 132-147

Time-varying treatment effects are considered in a nonparametric model with treatment endogeneity.

Quantitative Economics,
Vol. 11, pp. 161-202

Using a control function approach, weak instruments are characterized as a concurvity problem.

Quantitative Economics,
Vol. 10, pp. 1019-1068

In a set of nonlinear models, we propose reparametrization that facilitates robust inference under weak identification.

© Sukjin Han