Mean reversion in unemployment: new findings from the Baltic tigers

Abstract

The tendency of the unemployment rate to revert to the mean value or the natural rate of unemployment has been one of the most discussed topics in macroeconomics. This study focused on three Baltic countries–Estonia, Latvia and Lithuania–as case studies to investigate unemployment dynamics. Three unit root tests were performed for this purpose: 1) the Augmented Dickey-Fuller (ADF) test, 2) the Seemingly Unrelated Regressions Augmented Dickey-Fuller (SURADF) test and 3) the Fourier Augmented Dickey-Fuller (FADF) test. The null hypothesis was that unemployment in the Baltic countries is a unit root process. As the findings revealed, the ADF test and the SURADF test failed to reject the null hypothesis of a unit root for all the three Baltic countries. However, the nonlinear FADF test could not reject the null hypothesis for Lithuania. This means that unemployment in Lithuania could be described as a stationary process. As such, it has the tendency to revert to a sustainable level. By contrast, unemployment in Estonia and Latvia would be best characterised as a non-stationary process where the unemployment rate lacks the mean reverting behaviour.