The deviance information criterion in comparison of normal mixing models

Thomas Fung, Joanna J. J. Wang, Eugene Seneta

    Research output: Contribution to journalArticle

    1 Citation (Scopus)

    Abstract

    Model selection from several non-nested models by using the deviance information criterion within Bayesian inference Using Gibbs Sampling (BUGS) software needs to be treated with caution. This is particularly important if one can specify a model in various mixing representations, as for the normal variance-mean mixing distribution occurring in financial contexts. We propose a procedure to compare goodness of fit of several non-nested models, which uses BUGS software in part.

    Original languageEnglish
    Pages (from-to)411-421
    Number of pages11
    JournalInternational Statistical Review
    Volume82
    Issue number3
    DOIs
    Publication statusPublished - 1 Dec 2014

    Keywords

    • BUGS
    • DIC
    • financial models comparison
    • mixing representation
    • normal variance-mean distribution
    • Variance-Gamma distribution

    Fingerprint Dive into the research topics of 'The deviance information criterion in comparison of normal mixing models'. Together they form a unique fingerprint.

  • Cite this