A direct method for estimating a causal ordering in a linear non-Gaussian acyclic model
This addresses a bottleneck in causal inference for researchers, offering a more reliable method for analyzing causal relations in continuous variables, though it is incremental as it builds on existing non-Gaussianity-based approaches.
The paper tackles the problem of estimating causal orderings in linear non-Gaussian acyclic models, proposing a direct method that guarantees convergence to the correct solution within a fixed number of steps under model assumptions, unlike previous iterative approaches.
Structural equation models and Bayesian networks have been widely used to analyze causal relations between continuous variables. In such frameworks, linear acyclic models are typically used to model the datagenerating process of variables. Recently, it was shown that use of non-Gaussianity identifies a causal ordering of variables in a linear acyclic model without using any prior knowledge on the network structure, which is not the case with conventional methods. However, existing estimation methods are based on iterative search algorithms and may not converge to a correct solution in a finite number of steps. In this paper, we propose a new direct method to estimate a causal ordering based on non-Gaussianity. In contrast to the previous methods, our algorithm requires no algorithmic parameters and is guaranteed to converge to the right solution within a small fixed number of steps if the data strictly follows the model.