Nonparametric methods for inference in the presence of instrumental variables

Abstract

We suggest two nonparametric approaches, based on kernel methods and orthogonal series to estimating regression functions in the presence of instrumental variables. For the first time in this class of problems, we derive optimal convergence rates, and show that they are attained by particular estimators. In the presence of instrumental variables the relation that identifies the regression function also defines an ill-posed inverse problem, the ``difficulty'' of which depends on eigenvalues of a certain integral operator which is determined by the joint density of endogenous and instrumental variables. We delineate the role played by problem difficulty in determining both the optimal convergence rate and the appropriate choice of smoothing parameter.

Published at http://dx.doi.org/10.1214/009053605000000714 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

Cited by in corpus (37)

• Methodology and convergence rates for functional linear regression
• Endogeneity in high dimensions
• Local Identification of Nonparametric and Semiparametric Models
• Optimal Sup-norm Rates and Uniform Inference on Nonlinear Functionals of Nonparametric IV Regression
• Nonlinear estimation for linear inverse problems with error in the operator
• Testing Regression Monotonicity in Econometric Models
• Quasi-Bayesian analysis of nonparametric instrumental variables models
• Intrinsic Riemannian Functional Data Analysis
• Iterative Estimation of Solutions to Noisy Nonlinear Operator Equations in Nonparametric Instrumental Regression
• Counterfactual Prediction with Deep Instrumental Variables Networks
• Posterior consistency of nonparametric conditional moment restricted models
• Goodness-of-Fit Tests based on Series Estimators in Nonparametric Instrumental Regression
• Minimax Estimation of Conditional Moment Models
• Dual Instrumental Variable Regression
• Honest Confidence Sets in Nonparametric IV Regression and Other Ill-Posed Models
• Instrumental Variable Regression via Kernel Maximum Moment Loss
• A Projection Framework for Testing Shape Restrictions That Form Convex Cones
• Theory for identification and Inference with Synthetic Controls: A Proximal Causal Inference Framework
• Nonparametric instrumental regression with non-convex constraints
• Is completeness necessary? Estimation in nonidentified linear models
• Oracle Inequality for Instrumental Variable Regression
• Uniform Inference for Characteristic Effects of Large Continuous-Time Linear Models
• On rate optimal local estimation in nonparametric instrumental regression
• Uniform confidence bands for nonparametric errors-in-variables regression
• Nonparametric Instrumental Variables Estimation Under Misspecification
• On ill-posedness of nonparametric instrumental variable regression with convexity constraints
• Nonparametric Identification and Estimation with Independent, Discrete Instruments
• Optimal Linear Instrumental Variables Approximations
• Detecting Heterogeneous Treatment Effect with Instrumental Variables
• Functional linear instrumental regression under second order stationarity
• Optimal Global Test for Functional Regression
• Adaptive estimation of functionals in nonparametric instrumental regression
• Identification and Estimation of Heterogeneous Treatment Effects under Non-compliance or Non-ignorable assignment
• Exponentially tilted likelihood inference on growing dimensional unconditional moment models
• Deep learning for inverse problems with unknown operator
• Penalized Sieve GEL for Weighted Average Derivatives of Nonparametric Quantile IV Regressions
• The ET Interview: Professor Joel L. Horowitz