We study low dimensional complier parameters that are identified using a binary instrumental variable $Z$, which is valid conditional on a possibly high dimensional vector of covariates $X$. We characterize the doubly robust moment function for the entire class of complier parameters defined by Abadie (2003) by combining two classic formulations: the Wald formula and the $\kappa$ weight. In particular, we reinterpret the $\kappa$ weight as the Riesz representer to the Wald formula, which appears to be a new insight. The main result includes new cases such as average complier characteristics. We use the main result to propose a hypothesis test, free of functional form restrictions, to evaluate (i) whether two different instruments induce com...
We show that the Wald statistic still identifies a causal effect if instrument monotonicity is repla...
Standard causal inference characterizes treatment effect through averages, but the counterfactual di...
We derive general, yet simple, sharp bounds on the size of the omitted variable bias for a broad cla...
This paper investigates the local average treatment effect (LATE) with high-dimensional covariates, ...
We derive general, yet simple, sharp bounds on the size of the omitted variable bias for a broad cla...
Due to concerns about parametric model misspecification, there is interest in using machine learning...
I develop a new identification strategy for treatment effects when noisy measurements of unobserved ...
In heterogeneous treatment effect models with endogeneity, identification of the LATE typically rel...
Many proposals for the identification of causal effects in the presence of unmeasured confounding re...
Suppose we are interested in the mean of an outcome that is subject to nonignorable nonresponse. Thi...
In this paper, I consider identification of treatment effects whenthe treatment is endogenous. The u...
We show that the Wald statistic still identifies a causal effect if instrument monotonicity is repla...
The instrumental variable method relies on a strong "no-defiers" condition, which requires that the...
The nonparametric identification of the local average treatment effect (LATE) hinges on the satisfa...
In the presence of an endogenous binary treatment and a valid binary instru- ment, causal effects a...
We show that the Wald statistic still identifies a causal effect if instrument monotonicity is repla...
Standard causal inference characterizes treatment effect through averages, but the counterfactual di...
We derive general, yet simple, sharp bounds on the size of the omitted variable bias for a broad cla...
This paper investigates the local average treatment effect (LATE) with high-dimensional covariates, ...
We derive general, yet simple, sharp bounds on the size of the omitted variable bias for a broad cla...
Due to concerns about parametric model misspecification, there is interest in using machine learning...
I develop a new identification strategy for treatment effects when noisy measurements of unobserved ...
In heterogeneous treatment effect models with endogeneity, identification of the LATE typically rel...
Many proposals for the identification of causal effects in the presence of unmeasured confounding re...
Suppose we are interested in the mean of an outcome that is subject to nonignorable nonresponse. Thi...
In this paper, I consider identification of treatment effects whenthe treatment is endogenous. The u...
We show that the Wald statistic still identifies a causal effect if instrument monotonicity is repla...
The instrumental variable method relies on a strong "no-defiers" condition, which requires that the...
The nonparametric identification of the local average treatment effect (LATE) hinges on the satisfa...
In the presence of an endogenous binary treatment and a valid binary instru- ment, causal effects a...
We show that the Wald statistic still identifies a causal effect if instrument monotonicity is repla...
Standard causal inference characterizes treatment effect through averages, but the counterfactual di...
We derive general, yet simple, sharp bounds on the size of the omitted variable bias for a broad cla...