Causal Reasoning in Graphical Time Series Models

Abstract

We propose a definition of causality for time series in terms of the effect of an intervention in one component of a multivariate time series on another component at some later point in time. Conditions for identifiability, comparable to the back-door and front-door criteria, are presented and can also be verified graphically. Computation of the causal effect is derived and illustrated for the linear case.

Cite

Text

Eichler and Didelez. "Causal Reasoning in Graphical Time Series Models." Conference on Uncertainty in Artificial Intelligence, 2007. doi:10.5555/3020488.3020502

Markdown

[Eichler and Didelez. "Causal Reasoning in Graphical Time Series Models." Conference on Uncertainty in Artificial Intelligence, 2007.](https://mlanthology.org/uai/2007/eichler2007uai-causal/) doi:10.5555/3020488.3020502

BibTeX

@inproceedings{eichler2007uai-causal,
  title     = {{Causal Reasoning in Graphical Time Series Models}},
  author    = {Eichler, Michael and Didelez, Vanessa},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  year      = {2007},
  pages     = {109-116},
  doi       = {10.5555/3020488.3020502},
  url       = {https://mlanthology.org/uai/2007/eichler2007uai-causal/}
}