Unit Roots Tests with Smooth Breaks: An Application to the Nelson-Plosser Data Set

This paper reconsiders the nature of the trends (i.e. deterministic or stochastic) in macroeconomic time series. For this purpose, the paper employs two new tests that display robustness to structural breaks of unknown forms, irrespective of the date and/or location of the breaks. These tests approximate structural changes as smooth processes via Flexible Fourier transforms. The tests deliver strong evidence in favor of a nonlinear deterministic trend for real GNP, real per capita GNP, employment, the unemployment rate, and stock prices. Further, the two tests confirm the existence of stochastic trends in nominal GNP, consumer prices, real wages, monetary aggregates, velocity, and bond yields. In general, it appears that real variables are stationary while nominal ones have a unit root.