LASSO Inference for High Dimensional Predictive Regressions

TL;DR

This paper introduces the XDlasso, a novel estimator that corrects for both shrinkage and Stambaugh biases in high-dimensional predictive regressions with nonstationary data, enabling valid inference.

Contribution

The paper proposes the XDlasso estimator, which eliminates multiple biases without prior knowledge of regressors' stationarity, and establishes its asymptotic properties for hypothesis testing.

Findings

XDlasso effectively corrects biases in simulations.

Theoretical properties of XDlasso are validated through Monte Carlo studies.

Application to real data demonstrates its practical usefulness.

Abstract

LASSO inflicts shrinkage bias on estimated coefficients, which undermines asymptotic normality and invalidates standard inferential procedures based on the t-statistic. Given cross sectional data, the desparsified LASSO has emerged as a well-known remedy for correcting the shrinkage bias. In the context of high dimensional predictive regression, the desparsified LASSO faces an additional challenge: the Stambaugh bias arising from nonstationary regressors modeled as local unit roots. To restore standard inference, we propose a novel estimator called IVX-desparsified LASSO (XDlasso). XDlasso simultaneously eliminates both shrinkage bias and Stambaugh bias and does not require prior knowledge about the identities of nonstationary and stationary regressors. We establish the asymptotic properties of XDlasso for hypothesis testing, and our theoretical findings are supported by Monte Carlo simulations. Applying our method to real-world applications from the FRED-MD database, we investigate two important empirical questions: (i) the predictability of the U.S. stock returns based on the earnings-price ratio, and (ii) the predictability of the U.S. inflation using the unemployment.