We develop a Stata command csa2sls that implements the complete subset averaging two-stage least squares (CSA2SLS) estimator in Lee and Shin (2021). The CSA2SLS estimator is an alternative to the two-stage least squares estimator that remedies the bias issue caused by many correlated instruments. We conduct Monte Carlo simulations and confirm that the CSA2SLS estimator reduces both the mean squared error and the estimation bias substantially when instruments are correlated. We illustrate the usage of csa2sls in Stata by an empirical application. [arXiv][Journal (open access)] December 2023, The Stata Journal

     Working Papers:

Statistical inference of heterogeneous treatment effects (HTEs) is confounded when  economic units interact because treatment effects may vary by pre-treatment variables, post-treatment variables (that measure the exposure to other units’ treatment statuses), or both. It invalidates the standard hypothesis testing techniques used to infer HTEs. In this paper, I develop statistical inference  methods  to detect HTEs and disentangle the drivers of treatment effects heterogeneity in populations where units interact. Specifically, I incorporate clustered interaction into the potential outcomes model and propose kernel-based test statistics for the null hypotheses of (a) no HTEs by treatment assignment (or post-treatment exposure variables) for all pre-treatment variables values; and (b) no HTEs by pre-treatment variables for all treatment assignment vectors. To disentangle the source of heterogeneity in treatment effects, I recommend a multiple-testing algorithm.  I prove the asymptotic properties of the proposed test statistics via a  modern poissonization technique. Furthermore, I propose bootstrap methods that better approximate the null distributions in finite-sample settings. Monte Carlo simulation evidence corroborates the theoretical findings in the paper. Finally, to gain practical insight, I illustrate the usage of the proposed tests in an empirical application using an experimental data set from a Chinese weather insurance program.  [Paper][Summary

In this paper we study treatment assignment rules in the presence of social interaction. We construct an analytical framework under the anonymous interaction assumption, where the decision problem becomes choosing a treatment fraction. We propose a multinomial empirical success (MES) rule that includes the empirical success rule of Manski (2004) as a special case. We investigate the non-asymptotic bounds of the expected utility based on the MES rule. Finally, we prove that the MES rule achieves the asymptotic optimality with the minimax regret criterion. [arXiv][Replication Code] reject & resubmit by Journal of Econometrics   New draft coming soon!

We design randomization tests of heterogeneous treatment effects when units interact on a single connected network. Our modeling strategy allows network interference into the potential outcomes framework using the concept of exposure mapping. We consider several null hypotheses representing different notions of homogeneous treatment effects. However, these hypotheses are not sharp due to nuisance parameters and multiple potential outcomes. To address the issue of multiple potential outcomes, we propose a conditional randomization method that expands on existing procedures. Our conditioning approach permits the use of treatment assignment as a conditioning variable, widening the range of application of the randomization method of inference. In addition, we propose techniques that overcome the nuisance parameter issue. We show that our resulting testing methods based on the conditioning procedure and the strategies for handling nuisance parameters are asymptotically valid. We demonstrate the testing methods using a network data set and also present the findings of a Monte Carlo study.  [arXiv][ Slides ] January 2024, submitted

     In Progress:

1.  Measuring the Impact of Financial Bailouts: An Intervention Analysis Approach. 

2.   endivregress: Estimating Treatment Effects with Endogenous Misreporting using Stata (with Augustine Denteh and Pierre Nguimkeu ).

3.   Matching under Ambiguity (with Sergei Filiasov).