Detecting determinism using recurrence quantification analysis: Three test procedures
In this paper we use the "Recurrence Quantification Analysis" proposed by Zbilut and Webber [Zbilut, J.P., Webber Jr., C.L., 1992. Embeddings and delays as derived from quantification of recurrence plots. Physics Letters A 171, 199-203] to develop three test procedures that allow us to detect general dependence and, from that, possible deterministic behavior underlying series. Based on the concept of "Percent of Determinism" we obtain three statistics that allow us to test for the null hypothesis of randomness. The results of the application of these procedures to a set of simulated and real series reveal good behavior in a wide variety of situations, including different sample sizes and series affected by noise.
References listed on IDEAS
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Mayfield, E Scott & Mizrach, Bruce, 1992. "On Determining the Dimension of Real-Time Stock-Price Data," Journal of Business & Economic Statistics, American Statistical Association, vol. 10(3), pages 367-374, July.
- Strozzi, Fernanda & Zaldı́var, José-Manuel & Zbilut, Joseph P, 2002. "Application of nonlinear time series analysis techniques to high-frequency currency exchange data," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 312(3), pages 520-538.
- Teresa Aparicio & Eduardo Pozo & Dulce Saura, 2002. "The nearest neighbour method as a test for detecting complex dynamics in financial series. An empirical application," Applied Financial Economics, Taylor & Francis Journals, vol. 12(7), pages 517-525.
- Jorge Belaire-Franch, & Dulce Contreras & Lorena Tordera-Lledo, 2002. "Assessing Non-Linear Structures in Real Exchange Rates Using Recurrence Plot Strategies," Computing in Economics and Finance 2002 239, Society for Computational Economics.