BCDAG: An R Package for Bayesian Structure and Causal Learning of Gaussian DAGs

2026/07/24

paper

Abstract

Directed acyclic graphs (DAGs) provide a powerful framework to represent dependence relationships among variables in multivariate settings; in addition, under causal assumptions on the underlying data generating mechanism, they allow for the identification and estimation of causal effects between variables even from pure observational data. In this setting, the process of inferring the DAG structure from the data is referred to as causal structure learning or causal discovery. We introduce BCDAG, an R package for Bayesian causal discovery and causal effect estimation from Gaussian observational data, based on the methodology proposed by Castelletti and Mascaro (2021). We summarize the main features of the underlying method and illustrate its implementation using real and simulated data. Our algorithms scale efficiently with the number of observations and, whenever the DAGs are sufficiently sparse, with the number of variables in the dataset. In addition, the package provides functions for convergence diagnostics and for visualizing and summarizing posterior inference.

Related

• BCDAG: An R package for Bayesian structure and Causal learning of Gaussian DAGs
• Towards Scalable Bayesian Learning of Causal DAGs
• A Full DAG Score-Based Algorithm for Learning Causal Bayesian Networks with Latent Confounders
• A novel framework extending cause-effect inference methods to multivariate causal discovery
• BayesDAG: Gradient-Based Posterior Inference for Causal Discovery