Detecting the direction of causal time series

By Jan Peters, Dominik Janzing, Arthur Gretton, Bernhard Schölkopf. 2009

42 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Signal Processing

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

In Cognitive Neuroscience

In Signal Processing

Citations in the corpus

The Arrow of Time in Multivariate Time Series (2016, methodology): “By assuming that the data generating process exhibits linear dynamics and non-Gaussian noise we were able to extend the results of Peters et al. (2009) to multiple dimensions.”
Causal Inference Using the Algorithmic Markov Condition (2008, background): “10[41] describes an asymmetry that sometimes helped to identi fy the direction in empirical time series.”
Causal Inference on Discrete Data Using Additive Noise Models (2009, methodology): “[14] apply the concept of ANMs to ARMA time”
On the Entropy Production of Time Series with Unidirectional Linearity (2009, methodology): “On 1180 empirical time series from EEGs [8] we where able to classify around 82% correctly when the parameters are set to yields decisions for about 4% of the time series.”
Towards a Learning Theory of Cause-Effect Inference (2015, methodology): “On the one hand, Peters et al. (2009) construct two Auto-Regressive Moving-Average (ARMA) models for each causal time series and time direction, and prefers the solution under which the model residuals are independent from the inferred cause.”
Causal Inference on Time Series using Restricted Structural Equation Models (2013, background): “In the one-dimensional linear case model (1) is time-reversible if and only if the noise is normally distributed [Peters et al., 2009].”
Seeing the Arrow of Time (2014, methodology): “[12] used it to successfully analyze the direction of time for EEG data.”
Identifying Cause and Effect on Discrete Data using Additive Noise Models (2010, background): “Janzing & Steudel (2009) give further theoretical support for this principle of causal inference using the concept of Kolmogorov complexity and Peters et al. (2009a) use this principle to detect whether a sample of a time series has been reversed.”
From Dependence to Causation (2016, methodology): “On the one hand, Peters et al. (2009) construct two AutoRegressive Moving-Average (ARMA) models for each causal time series and time direction, and prefers the solution under which the model residuals are independent from the inferred cause.”
Scalable Matrix-valued Kernel Learning for High-dimensional Nonlinear Multivariate Regression and Granger Causality (2012, background): “tivariate regression and structured output learning, (b) sparse learning for high-dimensional settings [7], and (c) multiple time series analysis [17] and associated temporal causal modeling problems [21, 16, 25]. We begin by considering the general problem of estimating an unknown non-linear functi”
Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence Statistical Tests for the Detection of the Arrow of Time in Vector Autoregressive Models (unknown): “Our experiments show that the statistical test considered has better predictive performance than previous methods from the literature based on tests of independence [Peters et al., 2009; Gretton et al., 2008].”