Synergy between an Improved Covariate Unit Root Test and Cross‐sectionally Dependent Panel Data Unit Root Tests

Abstract

This paper proposes the use of an improved covariate unit root test which exploits the cross-sectional dependence information when the panel data null hypothesis of a unit root is rejected. More explicitly, to increase the power of the test, we suggest the utilization of more than one covariate and offer several ways to select the "best" covariates from the set of potential covariates represented by the individuals in the panel. Monte Carlo simulations show that some of our methods work well compared to using only one covariate. Employing our methods, we investigate the Prebish-Singer hypothesis for nine commodity prices. Our results show that this hypothesis holds for all but the price of petroleum. JEL classification: C22, C23, C32Key words: covariate unit root test, cross-sectional dependence in panel data, point optimal test, squared correlation, power 1 We are grateful to two anonymous referees for useful comments. We are also grateful to participants at the 17th African Econometric Society meeting and seminar participants at

Explore Associations between Subjective Well-Being and Eco-Logical Footprints with Fixed Effects Panel Regressions

“…The first-generation panel unit root test is called the Levin-Lin-Chu (LLC) [41]. Im-Pesaran-Shin [42] and the Hadri [43] are the second-generation panel unit root tests. They minimized the size distortions and increased the power.…”