Nonparametric Inference with an Instrumental Variable under a Separable Binary Treatment Choice Model

TL;DR

This work tackles nonparametric inference for causal effects using an instrumental variable under a logit-separable binary treatment model, focusing on the ATT $\tau^*$. It introduces a variationally independent, observation-based parameterization and derives the full semiparametric efficiency theory, providing a closed-form efficient influence function (EIF) for $\tau^*$ when the instrument is binary. An EIF-based estimator with cross-fitting estimates all nuisance functions nonparametrically, achieving consistency, asymptotic normality, and semiparametric efficiency without restrictive parametric assumptions. The paper also offers a generative model and falsification implications to assess identifying assumptions, and validates the approach via simulations and a Job Corps application, with extensions to nonlinear effects, population-level treatment effects, and nonignorable missing data. Overall, the framework enhances robust, flexible IV-based inference under separable treatment mechanisms and supports principled falsification and extensions.

Abstract

Instrumental variable (IV) methods are widely used to infer treatment effects in the presence of unmeasured confounding. In this paper, we study nonparametric inference with an IV under a separable binary treatment choice model, which posits that the odds of the probability of taking the treatment, conditional on the instrument and the treatment-free potential outcome, factor into separable components for each variable. While nonparametric identification of smooth functionals of the treatment-free potential outcome among the treated, such as the average treatment effect on the treated, has been established under this model, corresponding nonparametric efficient estimation has proven elusive due to variationally dependent nuisance parameters defined in terms of counterfactual quantities. To address this challenge, we introduce a new variationally independent parameterization based on nuisance functions defined directly from the observed data. This parameterization, coupled with a novel fixed-point argument, enables the use of modern machine learning methods for nuisance function estimation. We characterize the semiparametric efficiency bound for any smooth functional of the treatment-free potential outcome among the treated and construct a corresponding semiparametric efficient estimator without imposing any unnecessary restriction on nuisance functions. Furthermore, we describe a straightforward generative model justifying our identifying assumptions and characterize empirically falsifiable implications of the framework to evaluate our assumptions in practical settings. Our approach seamlessly extends to nonlinear treatment effects, population-level effects, and nonignorable missing data settings. We illustrate our methods through simulation studies and an application to the Job Corps study.

Figures (2)

• Figure 1: A graphical illustration of the described generative model compatible with \ref{['(IV1)']}-\ref{['(IV4)']}. The measured covariates $\bm{X}$ are suppressed for brevity.
• Figure 2: A Graphical Summary of the Simulation Results. The left and right panels correspond to the DGPs with continuous and binary $Y$, respectively. In the top panel, boxplots show the bias of each estimator for sample sizes $N \in \{1000,2000,4000\}$. The bottom panel presents numerical summaries for $\widehat{\tau}$. Each row shows the empirical bias, empirical standard error (ESE), asymptotic standard error based on the proposed variance estimator (ASE), and the empirical coverage rate of 95% confidence intervals computed using the ASE. Biases and standard errors are scaled by a factor of 10.

Theorems & Definitions (20)

• Theorem 3.1
• Theorem 3.2
• Theorem 4.1
• Theorem 4.2
• Theorem 5.1
• Theorem 6.1
• Theorem A.1
• Theorem A.2
• Theorem A.3
• Theorem A.4