Hide metadata

dc.date.accessioned2020-03-28T19:15:35Z
dc.date.available2020-03-28T19:15:35Z
dc.date.created2020-03-20T11:23:52Z
dc.date.issued2019
dc.identifier.citationCremaschi, Andrea Argiento, Raffaele Shoemaker, Katherine Peterson, Christine Vannucci, Marina . Hierarchical Normalized Completely Random Measures for Robust Graphical Modeling. Bayesian Analysis. 2019, 14(4), 1271-1301
dc.identifier.urihttp://hdl.handle.net/10852/74256
dc.description.abstractGaussian graphical models are useful tools for exploring network structures in multivariate normal data. In this paper we are interested in situations where data show departures from Gaussianity, therefore requiring alternative modeling distributions. The multivariate t-distribution, obtained by dividing each component of the data vector by a gamma random variable, is a straightforward generalization to accommodate deviations from normality such as heavy tails. Since different groups of variables may be contaminated to a different extent, Finegold and Drton (2014) introduced the Dirichlet t-distribution, where the divisors are clustered using a Dirichlet process. In this work, we consider a more general class of nonparametric distributions as the prior on the divisor terms, namely the class of normalized completely random measures (NormCRMs). To improve the effectiveness of the clustering, we propose modeling the dependence among the divisors through a nonparametric hierarchical structure, which allows for the sharing of parameters across the samples in the data set. This desirable feature enables us to cluster together different components of multivariate data in a parsimonious way. We demonstrate through simulations that this approach provides accurate graphical model inference, and apply it to a case study examining the dependence structure in radiomics data derived from The Cancer Imaging Atlas
dc.languageEN
dc.publisherInternational Society for Bayesian Analysis
dc.titleHierarchical Normalized Completely Random Measures for Robust Graphical Modeling
dc.typeJournal article
dc.creator.authorCremaschi, Andrea
dc.creator.authorArgiento, Raffaele
dc.creator.authorShoemaker, Katherine
dc.creator.authorPeterson, Christine
dc.creator.authorVannucci, Marina
cristin.unitcode185,51,15,0
cristin.unitnameAvdeling for biostatistikk
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode1
dc.identifier.cristin1802605
dc.identifier.bibliographiccitationinfo:ofi/fmt:kev:mtx:ctx&ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Bayesian Analysis&rft.volume=14&rft.spage=1271&rft.date=2019
dc.identifier.jtitleBayesian Analysis
dc.identifier.volume14
dc.identifier.issue4
dc.identifier.startpage1271
dc.identifier.endpage1301
dc.identifier.doihttps://doi.org/10.1214/19-BA1153
dc.identifier.urnURN:NBN:no-77361
dc.type.documentTidsskriftartikkel
dc.type.peerreviewedPeer reviewed
dc.source.issn1936-0975
dc.identifier.fulltextFulltext https://www.duo.uio.no/bitstream/handle/10852/74256/1/euclid.ba.1553738429.pdf
dc.type.versionPublishedVersion


Files in this item

Appears in the following Collection

Hide metadata