Change-point detection in high-dimensional covariance structure

dc.bibliographicCitation.firstPage3254eng
dc.bibliographicCitation.issue2eng
dc.bibliographicCitation.journalTitleElectronic journal of statistics : EJSeng
dc.bibliographicCitation.lastPage3294eng
dc.bibliographicCitation.volume12eng
dc.contributor.authorAvanesov, Valeriy
dc.contributor.authorBuzun, Nazar
dc.date.accessioned2022-06-21T12:15:29Z
dc.date.available2022-06-21T12:15:29Z
dc.date.issued2018
dc.description.abstractIn this paper we introduce a novel approach for an important problem of break detection. Specifically, we are interested in detection of an abrupt change in the covariance structure of a high-dimensional random process – a problem, which has applications in many areas e.g., neuroimaging and finance. The developed approach is essentially a testing procedure involving a choice of a critical level. To that end a non-standard bootstrap scheme is proposed and theoretically justified under mild assumptions. Theoretical study features a result providing guaranties for break detection. All the theoretical results are established in a high-dimensional setting (dimensionality p≫n). Multiscale nature of the approach allows for a trade-off between sensitivity of break detection and localization. The approach can be naturally employed in an on-line setting. Simulation study demonstrates that the approach matches the nominal level of false alarm probability and exhibits high power, outperforming a recent approach.eng
dc.description.versionpublishedVersioneng
dc.identifier.urihttps://oa.tib.eu/renate/handle/123456789/9101
dc.identifier.urihttps://doi.org/10.34657/8139
dc.language.isoengeng
dc.publisherIthaca, NY : Cornell University Libraryeng
dc.relation.doihttps://doi.org/10.1214/18-EJS1484
dc.relation.essn1935-7524
dc.rights.licenseCC BY 4.0 Unportedeng
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/eng
dc.subject.ddc310eng
dc.subject.otherBootstrapeng
dc.subject.otherCritical valueeng
dc.subject.otherMultiscaleeng
dc.subject.otherPrecision matrixeng
dc.subject.otherStructural changeeng
dc.titleChange-point detection in high-dimensional covariance structureeng
dc.typeArticleeng
dc.typeTexteng
tib.accessRightsopenAccesseng
wgl.contributorWIASeng
wgl.subjectMathematikeng
wgl.typeZeitschriftenartikeleng
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Change-point_detection.pdf
Size:
458.43 KB
Format:
Adobe Portable Document Format
Description:
Collections