A survey on cycles and chaos (part I)

Abstract

There are two contracting viewpoints concerning the explanation of observed fluctuations in economic and financial markets. According to the first view (Newclassical) the main source of fluctuations is to be found in exogenous, random shocks to fundamentals. According to the second view (Keynesian) a significant part of observed fluctuations is caused by non-linear economic laws. Even in the absence of any external shocks, non-linear market laws can generate endogenous business fluctuations. The discovery of chaotic, seemingly random looking dynamical behaviour in simple deterministic models sheds important new light on this debate. In order to detect non-linear structures in economic and financial data a certain number of tests, some based on chaos theory, have been developed. In this paper, we will briefly discuss several statistical techniques devised to detect independence and non-linearity in time-series data (part I). In a next issue of the journal, we shall also try to make a simple presentation of the basic notions of chaos, and then describe the related econometric tools (part II).