Random walks and non-linear paths in macroeconomic time series: Some evidence and implications

This paper investigates whether the inherent non-stationarity of macroeconomic time series is entirely due to a random walk or also to non-linear components. Applying the numerical tools of the analysis of dynamical systems to long time series for the United States, we reject the hypothesis that these series are generated solely by a linear stochastic process. Contrary to Real Business Cycle theory, that attributes the irregular behavior of the system to exogenous random factors, we maintain that the fluctuations in the time series cannot be explained only by means of external shocks plugged into linear autoregressive models. A dynamic and non-linear explanation may be useful for the double aim of describing and forecasting more accurately the evolution of the system. Linear macroeconomic models that find empirical verification on linear econometric analysis are therefore seriously called in question. On the contrary non-linear dynamical models may enable us to educe more complete information about economic phenomena from the same data sets used in the empirical analysis from Real Business Cycle Theory. We conclude that Real Business Cycle theory, and the unit root autoregressive models in general, are an inadequate device for a satisfactory understanding of economic time series. A theoretical approach grounded on non-linear metric methods, may however allow to identify non-linear structures that endogenously generate fluctuations in macroeconomic time series.