Flexible Fourier Stationary Test in GDP per capita for Central Eastern European Countries*

The main goal of the paper is to investigate whether real GDP follows a trend stationary or a different stationary process. Our hypothesis is that real output is characterized by a non-linear mean reverting process. It is flexible Fourier stationary unit root test proposed by Enders and Lee (2004, 2009) to assess the nonstationary properties of the real GDP per capita that has been applied for nine Central Eastern-European Countries from 1969 to 2009. The results of our research have proved that Fourier stationary unit root test has higher power than linear method if the true data generating process of per capita real GDP is in fact a stationary non-liner process of an unknown form with structural change using the low frequency components. The investigation of the stationary of per capita real GDP from the non-linear point of view provides strong evidence clearly indicating that real output is well characterized by a non-linear mean reverting process, namely in Bulgaria, Latvia and Romania. The evidence is that these three countries are nonlinear stationary, implying that per capita real GDP follows a steady rate of growth, and policy innovations rather then have temporary effects. These results have important policy implications for macroeconomic policy, modeling, testing and forecasting for Central Eastern-European Countries.