Robust Estimation and Inference for High-Dimensional Panel Data Models

TL;DR

This paper develops a comprehensive toolkit for robust estimation and inference in high-dimensional panel data models, accommodating complex error structures and growing regressors, with theoretical guarantees and practical applications.

Contribution

It introduces new estimation methods and concentration inequalities for high-dimensional panel data, enabling robust inference under complex error dependencies and large regressors.

Findings

Non-asymptotic bounds for LASSO estimator

Asymptotic normality via node-wise LASSO regression

Sharp convergence rates for thresholded HAC estimator

Abstract

This paper provides the relevant literature with a complete toolkit for conducting robust estimation and inference about the parameters of interest involved in a high-dimensional panel data framework. Specifically, (1) we allow for non-Gaussian, serially and cross-sectionally correlated and heteroskedastic error processes, (2) we develop an estimation method for high-dimensional long-run covariance matrix using a thresholded estimator, (3) we also allow for the number of regressors to grow faster than the sample size. Methodologically and technically, we develop two Nagaev--types of concentration inequalities: one for a partial sum and the other for a quadratic form, subject to a set of easily verifiable conditions. Leveraging these two inequalities, we derive a non-asymptotic bound for the LASSO estimator, achieve asymptotic normality via the node-wise LASSO regression, and establish a sharp convergence rate for the thresholded heteroskedasticity and autocorrelation consistent (HAC) estimator. We demonstrate the practical relevance of these theoretical results by investigating a high-dimensional panel data model with interactive effects. Moreover, we conduct extensive numerical studies using simulated and real data examples.