Causal Inference from Slowly Varying Nonstationary Processes

TL;DR

This paper introduces a novel causal inference method for nonstationary time series using a time-varying filter model and spectral analysis, enabling causal identification in complex, evolving systems.

Contribution

It develops a new class of restricted SCM tailored for nonstationary processes and leverages spectral estimates for causal inference, extending existing stationary methods.

Findings

Effective causal inference demonstrated on synthetic datasets.

Method outperforms traditional stationary approaches.

Applicable to high-order, non-smooth filters.

Abstract

Causal inference from observational data following the restricted structural causal models (SCM) framework hinges largely on the asymmetry between cause and effect from the data generating mechanisms, such as non-Gaussianity or non-linearity. This methodology can be adapted to stationary time series, yet inferring causal relationships from nonstationary time series remains a challenging task. In this work, we propose a new class of restricted SCM, via a time-varying filter and stationary noise, and exploit the asymmetry from nonstationarity for causal identification in both bivariate and network settings. We propose efficient procedures by leveraging powerful estimates of the bivariate evolutionary spectra for slowly varying processes. Various synthetic and real datasets that involve high-order and non-smooth filters are evaluated to demonstrate the effectiveness of our proposed methodology.