A Bayesian hierarchical copula model (Q2219218): Difference between revisions

The authors of the paper propose a \textit{Bayesian hierarchical copula model} to accommodate hierarchical structures of dependent data, where the subject-level dependence is modeled by the copula-based model and the hierarchical structure is described using random dependence parameters. The issues concerning inferences and the sample schemes are examined. The selection of transformation functions and associated scaling parameters are discussed. Simulation studies are presented to evaluate the finite sample performance of the proposed methods. The particular data set is analysed using the proposed \textit{Bayesian hierarchical copula model}. The proposed model unifies the ideas of the Bayesian hierarchical approach and the copula-based dependence modelling and offers the flexibility in facilitating various association structures, while allowing a straightforward implementation of the inference procedures.