Research

Research interests

Job market paper

Randomized experiments have become a standard tool in economics. In analyzing randomized experiments, the traditional approach has been based on the Stable Unit Treatment Value (SUTVA: Rubin (1990)) assumption which dictates that there is no interference between individuals. However, the SUTVA assumption fails to hold in many applications due to social interaction, general equilibrium, and/or externality effects. While much progress has been made in relaxing the SUTVA assumption, most of this literature has only considered a setting with perfect compliance to treatment assignment. In practice, however, noncompliance occurs frequently where the actual treatment receipt is different from the assignment to the treatment. In this paper, we study causal effects in randomized experiments with network interference and noncompliance. Spillovers are allowed to occur at both treatment choice stage and outcome realization stage. In particular, we explicitly model treatment choices of agents as a binary game of incomplete information where resulting equilibrium treatment choice probabilities affect outcomes of interest. Outcomes are further characterized by a random coefficient model to allow for general unobserved heterogeneity in the causal effects. After defining our causal parameters of interest, we propose a simple control function estimator and derive its asymptotic properties under large-network asymptotics. We apply our methods to the randomized subsidy program of Dupas (2014) where we find evidence of spillover effects on both short-run and long-run adoption of insecticide-treated bed nets. Finally, we illustrate the usefulness of our methods by analyzing the impact of counterfactual subsidy policies.

Working paper

Previous literature on instrumental variables method in a context of randomized experiment has assumed an exclusion restriction which states that an instrument does not directly affect an outcome of interest. In a clustered randomized experiments, this assumption fails to hold when there is a spillover or interference across individuals. When the exclusion restriction fails, many causal parameters such as local average treatment effect (LATE) are not point-identified. In this paper, we show that in a clustered RCT with one-sided noncompliance, when we have a baseline information on outcome, point-identification of local causal effect for compliers, which is often the parameter of interest, is possible under a mild difference-in-difference (DID)-like assumption. Furthermore, we can identify an indirect effect of intervention for never-takers, which can be used to test whether there is spillover effect or not. We illustrate our method in our empirical analysis of a microcredit program in rural Morocco from Crépon et al., 2015, where we find an evidence of spillover effects. Our results therefore suggest that the exclusion restriction is likely to be violated in this setting.


Empirical researchers are often interested in not only whether a treatment affects an outcome of interest, but also how the treatment effect arises. Causal mediation analysis provides a formal framework to identify causal mechanisms through which a treatment affects an outcome. The most popular identification strategy relies on so-called sequential ignorability (SI) assumption which requires that there is no unobserved confounder that lies in the causal paths between the treatment and the outcome. Despite its popularity, such assumption is deemed to be too strong in many settings as it excludes the existence of unobserved confounders. This limitation has inspired recent literature to consider an alternative identification strategy based on an instrumental variable (IV). This paper discusses the identification of causal mediation effects in a setting with a binary treatment and a binary instrumental variable that is both assumed to be random. We show that while IV methods allow for the possible existence of unobserved confounders, additional monotonicity assumptions are required unless the strong constant effect is assumed. Furthermore, even when such monotonicity assumptions are satisfied, IV estimands are not necessarily equivalent to target parameters.

Online Appendix.  

Work in progress 

Network version of linear-in-means model is widely used in applied work to study the role of social interactions and peer effects empirically. However when the network is endogenous, the linear-in-means model produces biased estimates. In this paper, we propose a joint model of network formation and outcome determination under network-mediated social interactions. Network formation is modeled as a binary game of incomplete information. We propose a control function approach that can handle a high-dimensionality of network formation process.

 Publication