Usefulness and limitations of convergent cross sorting and continuity scaling methods for their application in simulated and real-world time series
Causality detection methods are valuable tools for detecting causal links in complex systems. The efficiency of continuity scaling (CS) and the convergent cross sorting (CSS) methods to detect causality was analysed. Usefulness and limitations of both methods in their application to simulated and re...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Royal Society
2023-07-01
|
| Series: | Royal Society Open Science |
| Subjects: | |
| Online Access: | https://royalsocietypublishing.org/doi/10.1098/rsos.221590 |
| _version_ | 1797782321251745792 |
|---|---|
| author | Adolfo D. Bahamonde Rodrigo M. Montes Pablo Cornejo |
| author_facet | Adolfo D. Bahamonde Rodrigo M. Montes Pablo Cornejo |
| author_sort | Adolfo D. Bahamonde |
| collection | DOAJ |
| description | Causality detection methods are valuable tools for detecting causal links in complex systems. The efficiency of continuity scaling (CS) and the convergent cross sorting (CSS) methods to detect causality was analysed. Usefulness and limitations of both methods in their application to simulated and real-world time series was explored under different scenarios. We find that CS is more robust and efficient than the CSS method for all simulated systems, even when increasing noise levels were considered. Both methods were not able to infer causality when time series with a marked difference in their main frequencies were analysed. Minimum time-series length required for the detection of a causal link depends on intrinsic system dynamics and on the method selected to detect it. Using simulated time series, only the CS method was capable to detect bidirectional causality. Causality detection, using the CS method, should at least include: (i) causality strength convergence analysis, (ii) statistical tests of significance, (iii) time-series standardization, and (iv) causality strength ratios as a strength indicator of relative causality between systems. Causality cannot be detected by either method in simulated time series that exhibit generalized synchronization. |
| first_indexed | 2024-03-13T00:09:19Z |
| format | Article |
| id | doaj.art-0f61fada52e142228fa66b0af7b361e6 |
| institution | Directory Open Access Journal |
| issn | 2054-5703 |
| language | English |
| last_indexed | 2024-03-13T00:09:19Z |
| publishDate | 2023-07-01 |
| publisher | The Royal Society |
| record_format | Article |
| series | Royal Society Open Science |
| spelling | doaj.art-0f61fada52e142228fa66b0af7b361e62023-07-12T14:54:32ZengThe Royal SocietyRoyal Society Open Science2054-57032023-07-0110710.1098/rsos.221590Usefulness and limitations of convergent cross sorting and continuity scaling methods for their application in simulated and real-world time seriesAdolfo D. Bahamonde0Rodrigo M. Montes1Pablo Cornejo2Interdisciplinary Center for Aquaculture Research (INCAR), University of Concepción, O’Higgins 1695, Concepción, ChileInterdisciplinary Center for Aquaculture Research (INCAR), University of Concepción, O’Higgins 1695, Concepción, ChileInterdisciplinary Center for Aquaculture Research (INCAR), University of Concepción, O’Higgins 1695, Concepción, ChileCausality detection methods are valuable tools for detecting causal links in complex systems. The efficiency of continuity scaling (CS) and the convergent cross sorting (CSS) methods to detect causality was analysed. Usefulness and limitations of both methods in their application to simulated and real-world time series was explored under different scenarios. We find that CS is more robust and efficient than the CSS method for all simulated systems, even when increasing noise levels were considered. Both methods were not able to infer causality when time series with a marked difference in their main frequencies were analysed. Minimum time-series length required for the detection of a causal link depends on intrinsic system dynamics and on the method selected to detect it. Using simulated time series, only the CS method was capable to detect bidirectional causality. Causality detection, using the CS method, should at least include: (i) causality strength convergence analysis, (ii) statistical tests of significance, (iii) time-series standardization, and (iv) causality strength ratios as a strength indicator of relative causality between systems. Causality cannot be detected by either method in simulated time series that exhibit generalized synchronization.https://royalsocietypublishing.org/doi/10.1098/rsos.221590causalityconvergent cross sortingcontinuity scalingmutual information |
| spellingShingle | Adolfo D. Bahamonde Rodrigo M. Montes Pablo Cornejo Usefulness and limitations of convergent cross sorting and continuity scaling methods for their application in simulated and real-world time series Royal Society Open Science causality convergent cross sorting continuity scaling mutual information |
| title | Usefulness and limitations of convergent cross sorting and continuity scaling methods for their application in simulated and real-world time series |
| title_full | Usefulness and limitations of convergent cross sorting and continuity scaling methods for their application in simulated and real-world time series |
| title_fullStr | Usefulness and limitations of convergent cross sorting and continuity scaling methods for their application in simulated and real-world time series |
| title_full_unstemmed | Usefulness and limitations of convergent cross sorting and continuity scaling methods for their application in simulated and real-world time series |
| title_short | Usefulness and limitations of convergent cross sorting and continuity scaling methods for their application in simulated and real-world time series |
| title_sort | usefulness and limitations of convergent cross sorting and continuity scaling methods for their application in simulated and real world time series |
| topic | causality convergent cross sorting continuity scaling mutual information |
| url | https://royalsocietypublishing.org/doi/10.1098/rsos.221590 |
| work_keys_str_mv | AT adolfodbahamonde usefulnessandlimitationsofconvergentcrosssortingandcontinuityscalingmethodsfortheirapplicationinsimulatedandrealworldtimeseries AT rodrigommontes usefulnessandlimitationsofconvergentcrosssortingandcontinuityscalingmethodsfortheirapplicationinsimulatedandrealworldtimeseries AT pablocornejo usefulnessandlimitationsofconvergentcrosssortingandcontinuityscalingmethodsfortheirapplicationinsimulatedandrealworldtimeseries |