Causal Consistency of Structural Equation Models

Abstract

Complex systems can be modelled at various levels of detail. Ideally, causal models of the same system should be consistent with one another in the sense that they agree in their predictions of the effects of interventions. We formalise this notion of consistency in the case of Structural Equation Models (SEMs) by introducing exact transformations between SEMs. This provides a general language to consider, for instance, the different levels of description in the following three scenarios: (a) models with large numbers of variables versus models in which the `irrelevant' or unobservable variables have been marginalised out; (b) micro-level models versus macro-level models in which the macro-variables are aggregate features of the micro-variables; (c) dynamical time series models versus models of their stationary behaviour. Our analysis stresses the importance of well specified interventions in the causal modelling process and sheds light on the interpretation of cyclic SEMs.

arXiv commentequal contribution between Rubenstein and Weichwald; accepted manuscript

Cited by in corpus (12)

• Causality for Machine Learning
• Foundations of Structural Causal Models with Cycles and Latent Variables
• Algorithmic Recourse: from Counterfactual Explanations to Interventions
• Causality in cognitive neuroscience: concepts, challenges, and distributional robustness
• Causal structure learning from time series: Large regression coefficients may predict causal links better in practice than small p-values
• Merging joint distributions via causal model classes with low VC dimension
• Quantifying intrinsic causal contributions via structure preserving interventions
• Compositional Abstraction Error and a Category of Causal Models
• Measurement Dependence Inducing Latent Causal Models
• Abstracting Probabilistic Models: A Logical Perspective
• Abstracting Causal Models
• Boxhead: A Dataset for Learning Hierarchical Representations