Abstract
Establishing the presence of coupling and interaction in weakly coupled systems, especially in the presence of noise and nonlinearity, is a difficult problem. In this chapter, we explore different measures to detect a relationship between two systems. We compare the sensitivity of the different measures to stochastic coupled systems, discontinuous chaotic systems and continuous chaotic systems. We then test the robustness of the detection of coupling in the presence of additive noise. In conclusion, we find that nonlinear methods are more sensitive to detecting coupling under ideal conditions. However, in the presence of noise, linear techniques are more robust.
| Original language | English (US) |
|---|---|
| Title of host publication | Handbook of Time Series Analysis |
| Subtitle of host publication | Recent Theoretical Developments and Applications |
| Publisher | Wiley - VCH Verlag GmbH & CO. KGaA |
| Pages | 265-282 |
| Number of pages | 18 |
| ISBN (Print) | 9783527406234 |
| DOIs | |
| State | Published - Dec 11 2006 |
Keywords
- Detecting coupling
- Linear and nonlinear systems
- Methods of detecting coupling
- Presence of noise and nonlinearity
- Time series analysis
- Uncoupled systems
- Weakly coupled systems