Does linearity in the dynamics of inflation gap and unemployment rate matter?

Abstract

This paper test the null hypothesis of linearity against a specific form of nonlinearity in the Data Generating Process (DGP) of the unemployment rate and the difference between the inflation rate (measured as the twelve months variation of CPI and CPIX1) and the inflation target, using twenty years of data (1990-2009) and time series models. The rejection of the null implies that the series has more than one regime or state. The regime switching process could explain the recent boom/bust of inflation observed during these years, or the unemployment rate after the Asian crisis, for instance. The main results are: it is not possible to reject linearity in the deviation of inflation from the inflation target. During the last twenty years, inflation has converged smoothly to the target without any regime switching. The speed of convergence to the target has been constant over the years and inflationary shocks have been dissolved with the usual degree of persistency. Finally, strong evidence is found against linearity in the unemployment rate. On the contrary, it fluctuates with high probability between states or regimes through time.