Context-Specific Causal Discovery for Categorical Data Using Staged Trees

by   Manuele Leonelli, et al.

Causal discovery algorithms aims at untangling complex causal relationships using observational data only. Here, we introduce new causal discovery algorithms based on staged tree models, which can represent complex and non-symmetric causal effects. To demonstrate the efficacy of our algorithms, we introduce a new distance, inspired by the widely used structural interventional distance, to quantify the closeness between two staged trees in terms of their corresponding causal inference statements. A simulation study highlights the efficacy of staged trees in uncovering complex, asymmetric causal relationship from data and a real-world data application illustrates their use in a practical causal analysis.


page 1

page 2

page 3

page 4


A step towards the applicability of algorithms based on invariant causal learning on observational data

Machine learning can benefit from causal discovery for interpretation an...

Discovering Context Specific Causal Relationships

With the increasing need of personalised decision making, such as person...

Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation

Discovery of causal relations from observational data is essential for m...

Ordinal Causal Discovery

Causal discovery for purely observational, categorical data is a long-st...

Asymmetric predictability in causal discovery: an information theoretic approach

Causal investigations in observational studies pose a great challenge in...

Highly Efficient Structural Learning of Sparse Staged Trees

Several structural learning algorithms for staged tree models, an asymme...

An Upper Bound for Random Measurement Error in Causal Discovery

Causal discovery algorithms infer causal relations from data based on se...

Please sign up or login with your details

Forgot password? Click here to reset