Consistent causal inference from time series with PC algorithm and its time-aware extension

DOI10.1007/S11222-023-10330-3MaRDI QIDQ6089224zbMATH OpenOpenAlexWikidataFDO

Authors Rahul Biswas, Somabha Mukherjee

Publication date 17 November 2023

Published in Statistics and Computing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2210.09038

zbMATH Keywords

causal inferenceconsistencytime seriesdirected acyclic graphmixing

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: The estimator of a causal directed acyclic graph (DAG) with the PC algorithm is known to be consistent based on independent and identically distributed samples. In this paper, we consider the scenario when the multivariate samples are identically distributed but not independent. A common example is a stationary multivariate time series. We show that under a standard set of assumptions on the underlying time series involving $ho$-mixing, the PC algorithm is consistent in this dependent sample scenario. Further, we show that for the popular time series models such as vector auto-regressive moving average and linear processes, consistency of the PC algorithm holds. We also prove the consistency for the Time-Aware PC algorithm, a recent adaptation of the PC algorithm for the time series scenario. Our findings are supported by simulations and benchmark real data analyses provided towards the end of the paper.

Recommendations

• Causal inference with multiple time series: principles and problems
• Estimating high-dimensional directed acyclic graphs with the PC-algorithm
• Learning local directed acyclic graphs based on multivariate time series data
• The reduced PC-algorithm: improved causal structure learning in large random networks
• Causal inference from time series: what can be learned from Granger causality

Cites work

• scientific article; zbMATH DE number 5968895 (Why is no real title available?)
• scientific article; zbMATH DE number 3886886 (Why is no real title available?)
• scientific article; zbMATH DE number 3942882 (Why is no real title available?)
• scientific article; zbMATH DE number 1134987 (Why is no real title available?)
• scientific article; zbMATH DE number 1975652 (Why is no real title available?)
• scientific article; zbMATH DE number 3083049 (Why is no real title available?)
• 10.1162/153244302760200696
• 10.1162/153244303321897717
• Basic properties of strong mixing conditions. A survey and some open questions
• Causal inference with multiple time series: principles and problems
• Causality. Models, reasoning, and inference
• Causation, prediction, and search
• Characterization and greedy learning of interventional Markov equivalence classes of directed acyclic graphs
• Equivalence and Synthesis of Causal Models
• Estimating high-dimensional directed acyclic graphs with the PC-algorithm
• Graphical modelling of multivariate time series
• On Granger causality and the effect of interventions in time series
• On Strong Mixing Conditions for Stationary Gaussian Processes
• Some mixing properties of time series models
• Survey and Evaluation of Causal Discovery Methods for Time Series
• The Stationary Bootstrap
• The estimation of the correlation coefficient of bivariate data under dependence: convergence analysis
• The max-min hill-climbing Bayesian network structure learning algorithm
• Uniform consistency in causal inference

Cited in

(3)

• Synergy-incorporated Bayesian Petri net: a method for mining ``and/or relation and synergy effect with application in probabilistic reasoning
• Tensor recovery in high-dimensional Ising models
• A constraint optimization approach to causal discovery from subsampled time series data

This page was built for publication: Consistent causal inference from time series with PC algorithm and its time-aware extension

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6089224)