Causal Reasoning in Graphical Time Series Models
This work addresses causality in time series for researchers in statistics and machine learning, but it appears incremental as it extends existing causal frameworks to time series.
The authors tackled the problem of defining and identifying causality in multivariate time series by proposing a definition based on interventions and presenting graphical conditions for identifiability, with computation derived for linear cases.
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.