A Critique on the Interventional Detection of Causal Relationships
This work addresses theoretical issues in causal inference for researchers, but it appears incremental as it builds on existing critiques without introducing new methods or empirical results.
The paper critiques the use of interventions in Pearl's causal models, arguing that they can lead to misinterpretations of causation, such as detecting spurious causal relationships or forming invalid structural causal models in natural situations.
Interventions are of fundamental importance in Pearl's probabilistic causality regime. In this paper, we will inspect how interventions influence the interpretation of causation in causal models in specific situation. To this end, we will introduce a priori relationships as non-causal relationships in a causal system. Then, we will proceed to discuss the cases that interventions can lead to spurious causation interpretations. This includes the interventional detection of a priori relationships, and cases where the interventional detection of causality forms structural causal models that are not valid in natural situations. We will also discuss other properties of a priori relations and SCMs that have a priori information in their structural equations.