Honest Confidence Sets in Nonparametric IV Regression and Other Ill-Posed Models

TL;DR

This paper introduces honest confidence sets for ill-posed econometric models, including nonparametric IV regression, using novel inferential methods that ensure uniform validity across a broad class of models.

Contribution

It develops new inferential techniques for ill-posed models that do not rely on the central limit theorem, ensuring honest confidence sets with uniform coverage.

Findings

Confidence sets have valid coverage properties.

Monte Carlo experiments show reasonable width and coverage.

Applied to U.S. data for Engel curves.

Abstract

This paper develops inferential methods for a very general class of ill-posed models in econometrics encompassing the nonparametric instrumental variable regression, various functional regressions, and the density deconvolution. We focus on uniform confidence sets for the parameter of interest estimated with Tikhonov regularization, as in Darolles, Fan, Florens, and Renault (2011). Since it is impossible to have inferential methods based on the central limit theorem, we develop two alternative approaches relying on the concentration inequality and bootstrap approximations. We show that expected diameters and coverage properties of resulting sets have uniform validity over a large class of models, i.e., constructed confidence sets are honest. Monte Carlo experiments illustrate that introduced confidence sets have reasonable width and coverage properties. Using U.S. data, we provide uniform confidence sets for Engel curves for various commodities.