Causal Inference on Time Series using Structural Equation Models
By Jan Peters, Dominik Janzing, Bernhard Schölkopf. 2012
23 citations recorded by the source corpus.
Causal inference uses observations to infer the causal structure of the data generating system. We study a class of functional models that we call Time Series Models with Independent Noise (TiMINo). These models require independent residual time series, whereas traditional methods like Granger causality exploit the variance of residuals. There are two main contributions: (1) Theoretical: By restricting the model class (e.g. to additive noise) we can provide a more general identifiability result than existing ones. This result incorporates lagged and instantaneous effects that can be nonlinear and do not need to be faithful, and non-instantaneous feedbacks between the time series. (2) Practical: If there are no feedback loops between time series, we propose an algorithm based on non-linear independence tests of time series. When the data are causally insufficient, or the data generating process does not satisfy the model assumptions, this algorithm may still give partial results, but mostly avoids incorrect answers. An extension to (non-instantaneous) feedbacks is possible, but not discussed. It outperforms existing methods on artificial and real data. Code can be provided upon request.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Bernhard Schölkopf
- Jan Peters
- Stefan Bauer
- Peter Buhlmann
- Niklas Pfister
- Yoshua Bengio
- Dominik Janzing
- Michel Besserve
Citations in the corpus
- Causal Models for Dynamical Systems (2020, background): “…and several extensions of SCMs have been proposed [Wiener, 1956, Granger, 1969, Schreiber, 2000, White and Lu, 2010, Hyttinen et al., 2013, Peters et al., 2013, Pfister et al., 2018b], mostly considering discrete time models such as vector autoregressive models [L¨utkepohl, 2007], for…”
- Invariant Causal Prediction for Sequential Data (2017, background): “sality for noninstantaneous causal relations (e.g., Granger, 1969; Lütkepohl, 2005). Other methods that are able to identify instantaneous effects (e.g., Chu and Glymour, 2008; Hyvärinen et al., 2008; Peters et al., 2013) often require nonlinearities or non-Gaussianity. Additionally, they need to mod”
- Statistical analysis of coupled time series with Kernel Cross-Spectral Density operators (2013, methodology): “Following [13, 18], our independence test can further be combined to recent developments in kernel time series prediction techniques [20] to define general and reliable multivariate causal inference techniques.”