A Formalism for the Dimensional Analysis of Time Series

Jose-Manuel Rey and Manuel Morán
Additional contact information
Jose-Manuel Rey: Universidad Complutense de Madrid
Manuel Morán: Universidad Complutense de Madrid

No 1331, Computing in Economics and Finance 1999 from Society for Computational Economics

Abstract: The possibility that low dimensional chaotic systems generate stochastic dynamics is now a standard idea in economics. As a consequence, modern time series analysis has among its primary goals the design and computer implementation of techniques for distinguishing complex deterministic dynamics from purely random processes. It is essential here to have some notion of dimension, since stochastic processes are considered high dimensional whereas interesting chaotic systems low. However, a well founded interpretation of the analysis is not available when the data have not been observed along an orbit of a smooth dynamical system, which is not plausible in economic time series. I propose a formalism for the rigorous analysis of dimension of scalar data monitored in any dynamical process, deterministic or stochastic. The formalism provides an interpretation of the dimensional analysis of ergodic processes while retaining the meaning of the classical dimensional test for the detection of chaos. We also show some applications to financial data.

New Economics Papers: this item is included in nep-ets
Date: 1999-03-01
View list of references

Downloads: (external link)
http://fmwww.bc.edu/cef99/papers/dimension.pdf main text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:sce:scecf9:1331

Access Statistics for this paper

More papers in Computing in Economics and Finance 1999 from Society for Computational Economics
Address: CEF99, Boston College, Department of Economics, Chestnut Hill MA 02467 USA
Contact information at EDIRC.
Series data maintained by Christopher F. Baum ().