Empirical eigenvalue based testing for structural breaks in linear panel data models

TL;DR

This paper introduces an eigenvalue-based test for detecting structural breaks in linear panel data models, capable of identifying changes in mean, covariance, or both, with proven consistency and demonstrated practical utility.

Contribution

It develops a novel test based on the largest eigenvalue of the covariance matrix for stability in panel data models, addressing gaps in existing methods.

Findings

Test effectively detects structural breaks in mean and covariance.

Simulation studies confirm the test's consistency and reliability.

Application to U.S. treasury data reveals insights into the 2007-2008 crisis.

Abstract

Testing for stability in linear panel data models has become an important topic in both the statistics and econometrics research communities. The available methodologies address testing for changes in the mean/linear trend, or testing for breaks in the covariance structure by checking for the constancy of common factor loadings. In such cases when an external shock induces a change to the stochastic structure of panel data, it is unclear whether the change would be reflected in the mean, the covariance structure, or both. In this paper, we develop a test for structural stability of linear panel data models that is based on monitoring for changes in the largest eigenvalue of the sample covariance matrix. The asymptotic distribution of the proposed test statistic is established under the null hypothesis that the mean and covariance structure of the panel data's cross sectional units remain stable during the observation period. We show that the test is consistent assuming common breaks in the mean or factor loadings. These results are investigated by means of a Monte Carlo simulation study, and their usefulness is demonstrated with an application to U.S. treasury yield curve data, in which some interesting features of the 2007-2008 subprime crisis are illuminated.