Automatic Debiased Machine Learning of Structural Parameters with General Conditional Moments

TL;DR

This paper introduces a machine learning-based method to automatically construct orthogonal moments for estimating structural parameters in models with conditional moment restrictions, ensuring debiased inference.

Contribution

It develops a novel approach to estimate Neyman-orthogonal moments using Lasso to solve functional equations, enabling straightforward implementation and valid inference.

Findings

The method achieves $\

The estimator is $\

Monte Carlo experiments validate the approach's effectiveness.

Abstract

This paper proposes a method to automatically construct or estimate Neyman-orthogonal moments in general models defined by a finite number of conditional moment restrictions (CMRs), with possibly different conditioning variables and endogenous regressors. CMRs are allowed to depend on non-parametric components, which might be flexibly modeled using Machine Learning tools, and non-linearly on finite-dimensional parameters. The key step in this construction is the estimation of Orthogonal Instrumental Variables (OR-IVs) -- "residualized" functions of the conditioning variables, which are then combined to obtain a debiased moment. We argue that computing OR-IVs necessarily requires solving potentially complicated functional equations, which depend on unknown terms. However, by imposing an approximate sparsity condition, our method finds the solutions to those equations using a Lasso-type program and can then be implemented straightforwardly. Based on this, we introduce a GMM estimator of finite-dimensional parameters (structural parameters) in a two-step framework. We derive theoretical guarantees for our construction of OR-IVs and show $\sqrt{n}$-consistency and asymptotic normality for the estimator of the structural parameters. Our Monte Carlo experiments and an empirical application on estimating firm-level production functions highlight the importance of relying on inference methods like the one proposed.