Causal Inference from Slowly Varying Nonstationary Processes
This work addresses the challenging problem of causal inference for nonstationary time series, which is a significant hurdle for researchers and practitioners working with real-world, time-evolving data.
This paper tackles the problem of causal inference from nonstationary time series by proposing a new class of restricted Structural Causal Models (SCM) that uses a time-varying filter and stationary noise. It exploits the asymmetry arising from nonstationarity to identify causal relationships in both bivariate and network settings.
Causal inference from observational data following the restricted structural causal model (SCM) framework hinges largely on the asymmetry between cause and effect from the data generating mechanisms, such as non-Gaussianity or nonlinearity. 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.