Show simple item record

dc.creatorLee, KY
dc.creatorLi, B
dc.creatorZhao, H
dc.date.accessioned2021-01-25T22:45:37Z
dc.date.available2021-01-25T22:45:37Z
dc.date.issued2016-09-01
dc.identifier.issn0006-3444
dc.identifier.issn1464-3510
dc.identifier.doihttp://dx.doi.org/10.34944/dspace/5014
dc.identifier.otherDX7WJ (isidoc)
dc.identifier.other29422689 (pubmed)
dc.identifier.urihttp://hdl.handle.net/20.500.12613/5032
dc.description.abstract© 2016 Biometrika Trust. We introduce an additive partial correlation operator as an extension of partial correlation to the nonlinear setting, and use it to develop a new estimator for nonparametric graphical models. Our graphical models are based on additive conditional independence, a statistical relation that captures the spirit of conditional independence without having to resort to high-dimensional kernels for its estimation. The additive partial correlation operator completely characterizes additive conditional independence, and has the additional advantage of putting marginal variation on appropriate scales when evaluating interdependence, which leads to more accurate statistical inference. We establish the consistency of the proposed estimator. Through simulation experiments and analysis of the DREAM4 Challenge dataset, we demonstrate that our method performs better than existing methods in cases where the Gaussian or copula Gaussian assumption does not hold, and that a more appropriate scaling for our method further enhances its performance.
dc.format.extent513-530
dc.language.isoen
dc.relation.haspartBiometrika
dc.relation.isreferencedbyOxford University Press (OUP)
dc.rightsAll Rights Reserved
dc.subjectAdditive conditional covariance operator
dc.subjectAdditive conditional independence
dc.subjectCopula
dc.subjectGaussian graphical model
dc.subjectPartial correlation
dc.subjectReproducing kernel
dc.titleOn an additive partial correlation operator and nonparametric estimation of graphical models
dc.typeArticle
dc.type.genrePost-print
dc.relation.doi10.1093/biomet/asw028
dc.ada.noteFor Americans with Disabilities Act (ADA) accommodation, including help with reading this content, please contact scholarshare@temple.edu
dc.date.updated2021-01-25T22:45:35Z
refterms.dateFOA2021-01-25T22:45:38Z


Files in this item

Thumbnail
Name:
On an additive partial correlation ...
Size:
277.7Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record