fedecastelletti Goto Github PK

bayes_learn_categorical_essential_graphs

bayes_learning_networks_interventional

Implements the methodology of Castelletti & Peluso (2022, Biometrika) for structure learning of directed networks from interventional experimental data.

bayes_networks_mixed_data

Implements a Bayesian semi-parametric methodology (based on Gaussian copulas) for structure learning of directed networks given mixed-type data.

bayes_probit_graphical_causal

Implements the Bayesian methodology of Castelletti & Consonni (2021, Bayesian Analysis) for structure learning and causal inference in probit graphical models.

bayes_structure_causal_categorical_graphs

Implements the Bayesian methodology of Castelletti et al. (2023+) for joint structure learning and causal effect estimation in categorical graphical models. Arxiv paper available at https://arxiv.org/abs/2306.16068.

bnp_mixture_causal_dags

Implements the methodology of Castelletti & Consonni (2022, Statistics in Medicine) for structure learning of Directed Acyclic Graphs and causal effect estimation in heterogeneous settings. The method is based on a Bayesian non-parametric mixture of DAG models.

network_structure_learning_uncertain_interventions

Implements the metodology of Castelletti and Peluso (2022, Journal of the American Statistical Association) for DAG structure learning from interventional data with unknown intervention targets.

obayes_learn_essential_graphs

obayes_learn_interv_essential_graphs

ssd_causal_discovery

Implements the methodology of Castelletti & Consonni (2023, Statistical Science) on Bayesian sample size determination for causal discovery based on Directed Acyclic Graphs (DAGs). Arxiv paper available at https://arxiv.org/abs/2206.00755