Causalized convergent cross-mapping and its approximate equivalence with directed information in causality analysis
PNAS Nexus · 21.12.2023 · 3 (1)
DOI: 10.1093/pnasnexus/pgad422 ↗Kurz gefasst
Fachartikel in der Zeitschrift PNAS Nexus, online erschienen am 07.12.2023. Verfasst von Jinxian Deng und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI 48824, USA. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS, National Science Foundation, National Institutes of Health.
Abstract (Originalsprache)
Convergent cross-mapping (CCM) has attracted increased attention recently due to its capability to detect causality in nonseparable systems under deterministic settings, which may not be covered by the traditional Granger causality. From an information-theoretic perspective, causality is often characterized as the directed information (DI) flowing from one side to the other. As information is essentially nondeterministic, a natural question is: does CCM measure DI flow? Here, we first causalize CCM so that it aligns with the presumption in causality analysis—the future values of one process cannot influence the past of the other, and then establish and validate the approximate equivalence of causalized CCM (cCCM) and DI under Gaussian variables through both theoretical derivations and fMRI-based brain network causality analysis. Our simulation result indicates that, in general, cCCM tends to be more robust than DI in causality detection. The underlying argument is that DI relies heavily on probability estimation, which is sensitive to data size as well as digitization procedures; cCCM, on the other hand, gets around this problem through geometric cross-mapping between the manifolds involved. Overall, our analysis demonstrates that cross-mapping provides an alternative way to evaluate DI and is potentially an effective technique for identifying both linear and nonlinear causal coupling in brain neural networks and other settings, either random or deterministic, or both.
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI 48824, USA.
- Department of Radiology, Michigan State University, East Lansing, MI 48824, USA.
- Department of Neuroscience, Michigan State University, East Lansing, MI 48824, USA.
- Department of Computer Science and Engineering, University of Texas, Arlington, TX 76010, USA.
- Institute for Exercise and Environmental Medicine, Texas Health Presbyterian Hospital Dallas, Dallas, TX 75231, USA.
- Departments of Neurology and Internal Medicine, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
ORCID-Profile: Norman Scheel, David C Zhu, Jian Ren, Tongtong Li, Rong Zhang
Förderung
- NIA NIH HHS
- National Science Foundation
- National Institutes of Health
Zitieren
APA
Deng, J., Sun, B., Scheel, N., Renli, A. B., Zhu, D. C., Zhu, D., Ren, J., Li, T., & Zhang, R. (2023). Causalized convergent cross-mapping and its approximate equivalence with directed information in causality analysis. PNAS Nexus, 3(1). https://doi.org/10.1093/pnasnexus/pgad422
Vancouver
Deng J, Sun B, Scheel N, Renli AB, Zhu DC, Zhu D, et al. Causalized convergent cross-mapping and its approximate equivalence with directed information in causality analysis. PNAS Nexus. 2023;3(1). doi:10.1093/pnasnexus/pgad422
BibTeX
@article{Deng2023,
author = {Deng, Jinxian and Sun, Boxin and Scheel, Norman and Renli, Alina B and Zhu, David C and Zhu, Dajiang and Ren, Jian and Li, Tongtong and Zhang, Rong},
title = {Causalized convergent cross-mapping and its approximate equivalence with directed information in causality analysis},
journal = {PNAS Nexus},
year = {2023},
volume = {3},
number = {1},
doi = {10.1093/pnasnexus/pgad422}
}
EUVIMED