Symbolic Time Series Analysis in Economics

In this paper I describe and apply the methods of Symbolic Time Series Analysis (STSA) to an experimental framework. The idea behind Symbolic Time Series Analysis is simple: the values of a given time series data are transformed into a finite set of symbols obtaining a finite string. Then, we can process the symbolic sequence using tools from information theory and symbolic dynamics. I discuss data symbolization as a tool for identifying temporal patterns in experimental data and use symbol sequence statistics in a model strategy. To explain these applications, I describe methods to select the symbolization of the data (Section 2), I introduce the symbolic sequence histograms and some tools to characterize and compare these histograms (Section 3). I show that the methods of symbolic time series analysis can be a good tool to describe and recognize time patterns in complex dynamical processes and to extract dynamical information about this kind of system. In particular, the method gives us a language in which to express and analyze these time patterns. In section 4 I report some applications of STSA to study the evolution of ifferent economies. In these applications data symbolization is based on economic criteria using the notion of economic regime introduced earlier in this thesis. I use STSA methods to describe the dynamical behavior of these economies and to do comparative analysis of their regime dynamics. In section 5 I use STSA to reconstruct a model of a dynamical system from measured time series data. In particular, I will show how the observed symbolic sequence statistics can be used as a target for measuring the goodness of fit of proposed models.