A panel cointegrating rank test with structural breaks and cross-sectional dependence

A new panel cointegrating rank test which allows for a linear time trend with breaks and cross-sectional dependence is proposed. The new correlation-augmented inverse normal (CAIN) test is based on a modification of the inverse normal method and combines the p-values of individual likelihood-ratio trace statistics by assuming that the number of breaks and break points are known. A Monte Carlo study demonstrates its robustness to cross-sectional dependence and its superior size and power properties compared to other meta-analytic tests used in practice. The test is applied to investigate the long-run relationship between regional house prices and personal income in the United States in view of the structural break introduced by the Global Financial Crisis. (C) 2020 The Author(s). Published by Elsevier B.V. on behalf of EcoSta Econometrics and Statistics.