UNIT ROOT TESTING IN WEEKLY PANELS OF TIME SERIES; IS IT APPLICABLE?

Testing for seasonal unit roots essentially means investigating the degree of reversion of seasonal cycles to time constant equilibrium patterns. We consider the problem of testing for seasonal unit roots in weekly panel data. To do this, we generalize the monthly CHEGY test to the weekly case. The problem is that test statistics fail to converge to their expected limiting distributions. All methods are applied to an empirical data obtained from tourism department in Nigeria. Tests currently available suffer from a combination of two serious shortcomings, size distortions and low power against credible alternatives