How Sure Are We About PPP? Panel Evidence with the Null of Stationary Real Exchange Rates

There has been serious suspicion of a spurious rejection of the unit roots in panel studies of PPP due to the failure to control for cross-sectional dependence. This article presents evidence of mean-reversion in industrial country real exchange rates in a set up that accounts naturally for cross-sectional dependence, is invariant to the benchmark currency and capable of detecting against regime changes, and actually tests for the null of interest, ie. the purchasing power parity. Our results are based on a KPSS test for the stationarity null generalized in a multivariate random walk plus noise model by Nyblom and Harvey (1998).