A Markov equivalence class contains all the Directed Acyclic Graphs (DAGs) encoding the same conditional independencies, and is represented by a Completed Partially Directed Acyclic Graph (CPDAG), also named Essential Graph (EG).We approach the problem of model selection among noncausal sparse Gaussian DAGs by directly scoring EGs, using an objective Bayes method. Specifically, we construct objective priors for model selection based on the Fractional Bayes Factor, leading to a closed form expression for the marginal likelihood of an EG. Next we propose an MCMC strategy to explore the space of EGs using sparsity constraints, and illustrate the performance of our method on simulation studies, as well as on a real dataset. Our method provides a coherent quantication of inferential uncertainty, requires minimal prior specication, and shows to be competitive in learning the structure of the data-generating EG when compared to alternative state-of-the-art algorithms.

Castelletti, F., Consonni, G., Della Vedova, M. L., Peluso, S., Learning Markov Equivalence Classes of Directed Acyclic Graphs: an Objective Bayes Approach, <<BAYESIAN ANALYSIS>>, 2018; 13 (4): 1231-1256. [doi:10.1214/18-BA1101] [http://hdl.handle.net/10807/118019]

Learning Markov Equivalence Classes of Directed Acyclic Graphs: an Objective Bayes Approach

Castelletti, Federico;Consonni, Guido;Della Vedova, Marco Luigi;Peluso, Stefano
2018

Abstract

A Markov equivalence class contains all the Directed Acyclic Graphs (DAGs) encoding the same conditional independencies, and is represented by a Completed Partially Directed Acyclic Graph (CPDAG), also named Essential Graph (EG).We approach the problem of model selection among noncausal sparse Gaussian DAGs by directly scoring EGs, using an objective Bayes method. Specifically, we construct objective priors for model selection based on the Fractional Bayes Factor, leading to a closed form expression for the marginal likelihood of an EG. Next we propose an MCMC strategy to explore the space of EGs using sparsity constraints, and illustrate the performance of our method on simulation studies, as well as on a real dataset. Our method provides a coherent quantication of inferential uncertainty, requires minimal prior specication, and shows to be competitive in learning the structure of the data-generating EG when compared to alternative state-of-the-art algorithms.
2018
Inglese
Castelletti, F., Consonni, G., Della Vedova, M. L., Peluso, S., Learning Markov Equivalence Classes of Directed Acyclic Graphs: an Objective Bayes Approach, <<BAYESIAN ANALYSIS>>, 2018; 13 (4): 1231-1256. [doi:10.1214/18-BA1101] [http://hdl.handle.net/10807/118019]
File in questo prodotto:
File Dimensione Formato  
Castelletti et al. 2018 BA.pdf

accesso aperto

Tipologia file ?: Versione Editoriale (PDF)
Licenza: Creative commons
Dimensione 679.93 kB
Formato Adobe PDF
679.93 kB Adobe PDF Visualizza/Apri
2018 Castelletti Consonni Della Vedova Peluso Bayesian Analysis Learning Markov Equiv.pdf

non disponibili

Tipologia file ?: Versione Editoriale (PDF)
Licenza: Non specificato
Dimensione 679.9 kB
Formato Unknown
679.9 kB Unknown   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10807/118019
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 21
  • ???jsp.display-item.citation.isi??? 21
social impact