Log In Sign Up

High-recall causal discovery for autocorrelated time series with latent confounders

by   Andreas Gerhardus, et al.

We present a new method for linear and nonlinear, lagged and contemporaneous constraint-based causal discovery from observational time series in the presence of latent confounders. We show that existing causal discovery methods such as FCI and variants suffer from low recall in the autocorrelated time series case and identify low effect size of conditional independence tests as the main reason. Information-theoretical arguments show that effect size can often be increased if causal parents are included in the conditioning sets. To identify parents early on, we suggest an iterative procedure that utilizes novel orientation rules to determine ancestral relationships already during the edge removal phase. We prove that the method is order-independent, and sound and complete in the oracle case. Extensive simulation studies for different numbers of variables, time lags, sample sizes, and further cases demonstrate that our method indeed achieves much higher recall than existing methods while keeping false positives at the desired level. This performance gain grows with stronger autocorrelation. Our method also covers causal discovery for non-time series data as a special case. We provide Python code for all methods involved in the simulation studies.


page 1

page 2

page 3

page 4


Discovering contemporaneous and lagged causal relations in autocorrelated nonlinear time series datasets

We consider causal discovery from time series using conditional independ...

Causal Discovery with General Non-Linear Relationships Using Non-Linear ICA

We consider the problem of inferring causal relationships between two or...

Structure Learning from Time Series with False Discovery Control

We consider the Granger causal structure learning problem from time seri...

Stimuli Dependent Synergy and Redundancy Dominated Causal Effects in Time Series

We characterize the degree of synergy- and redundancy-dominated causal i...

Data Generating Process to Evaluate Causal Discovery Techniques for Time Series Data

Going beyond correlations, the understanding and identification of causa...

Necessary and sufficient conditions for causal feature selection in time series with latent common causes

We study the identification of direct and indirect causes on time series...

Simulations evaluating resampling methods for causal discovery: ensemble performance and calibration

Causal discovery can be a powerful tool for investigating causality when...