Paper traces Granger tests toward causal structure in dynamical models
Original title: From Granger causality to causal structure in dynamical systems
The review says Granger tests detect predictive links among signals, not causal links among generating mechanisms.
An arXiv paper reviews observation-space Granger analysis and then examines directed structure in latent dynamical models. It asks under which conditions that structure can be read causally rather than as a predictive relation. The work is theoretical and reports no security incident or model release.
- Granger causality tests whether one signal's past improves prediction of another.
- The authors say the name can mislead readers about mechanism-level causality.
- The paper moves from measured signals to latent dynamical models.
From the original article
1 min read at arxiv.orgThe idea of testing whether the past of one signal improves the prediction of another can be traced back to Wiener. It was Granger who formalized the concept. Granger causality has become one of the most widely used tools to infer directed interactions between the components of a system.
By Víctor Elvira · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.