Testing for Stationarity in Panel Data when Errors are Serially Correlated. Finite-Sample Results

Abstract: In this paper, we study the small sample properties of the panel data stationarity test of Hadri (2000). We find that the previously suggested moments, that are to be used when standardizing the panel data stationarity test, cause size distortions when samples are small and serial correlation in the disturbance terms is allowed for. Instead, we supply standardizing moments that are to be used in a panel data stationarity test when samples are small and serial correlation in the disturbances may be an issue. We also document a serious small-sample bias in the panel data stationarity test when a linear trend is present in the data.