Shapes as Product Differentiation︎︎︎


with Eric Schulman, Kristen Grauman, Santhosh Ramakrishnan


arxiv︎︎︎  slides︎︎︎

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 ︎︎︎.



Sep 2024


new draft coming soon

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.



Sep 2024

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.



Mar 2024


new draft coming soon

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.


Feb 2024


new draft coming soon


The classic control function approach requires invertibility, which limits its applicability (e.g., discrete treatments). We allow the control function to be set-valued and derive sharp bounds on structural parameters.


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.



2023
Journal of American Statistical Association

Vol. 00, pp. 1-11
*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.


© Sukjin Han