Stochastic Simulation Inference Algorithm in Restricted Pair Copula Bayesian Network with Single Root Node

Panagiotis Basiouras Serrano and Dorota Kurowicka ()
Additional contact information
Panagiotis Basiouras Serrano: TU Delft, DIAM
Dorota Kurowicka: TU Delft, DIAM

A chapter in Statistical Dependence Modeling, 2026, pp 21-51 from Springer

Abstract: Abstract Bayesian Networks (BNs) are graphical models used to represent joint distributions. In this paper, we discuss copula-based BNs, where relationships between each node and its parents are defined through bivariate and conditional bivariate copulas, along with marginal densities. Under specific constraints on the graph structure, these models can be efficiently estimated and sampled (without the need for expensive integration). We focus on the problem of conditionalization in copula-based BNs, considering a network with a single root. The conditional distribution of a subset of nodes, given observed evidence from other nodes, is computed via sampling. Through a simulation study, we demonstrate that this approach is feasible for sufficiently sparse networks.

Keywords: Graphical models; Bayesian networks; Vine copula; Inference (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-032-14252-8_3

Ordering information: This item can be ordered from
http://www.springer.com/9783032142528

DOI: 10.1007/978-3-032-14252-8_3

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().