File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1145/3340804
- Scopus: eid_2-s2.0-85073122477
- WOS: WOS:000489839700003
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Bayesian Model Selection Approach to Multiple Change-Points Detection with Non-Local Prior Distributions
Title | Bayesian Model Selection Approach to Multiple Change-Points Detection with Non-Local Prior Distributions |
---|---|
Authors | |
Keywords | Bayesian networks Magnetic resonance imaging Parallel processing systems Bayes factor Bayesian model selection |
Issue Date | 2019 |
Publisher | Association for Computing Machinery, Inc. The Journal's web site is located at http://tkdd.cs.uiuc.edu |
Citation | ACM Transactions on Knowledge Discovery from Data, 2019, v. 13 n. 5, p. article no. 48 How to Cite? |
Abstract | We propose a Bayesian model selection (BMS) boundary detection procedure using non-local prior distributions for a sequence of data with multiple systematic mean changes. By using the non-local priors in the BMS framework, the BMS method can effectively suppress the non-boundary spike points with large instantaneous changes. Further, we speedup the algorithm by reducing the multiple change points to a series of single change point detection problems. We establish the consistency of the estimated number and locations of the change points under various prior distributions. From both theoretical and numerical perspectives, we show that the non-local inverse moment prior leads to the fastest convergence rate in identifying the true change points on the boundaries. Extensive simulation studies are conducted to compare the BMS with existing methods, and our method is illustrated with application to the magnetic resonance imaging guided radiation therapy data. |
Persistent Identifier | http://hdl.handle.net/10722/279508 |
ISSN | 2023 Impact Factor: 4.0 2023 SCImago Journal Rankings: 1.303 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jiang, F | - |
dc.contributor.author | Yin, G | - |
dc.contributor.author | Dominici, F | - |
dc.date.accessioned | 2019-11-01T07:18:42Z | - |
dc.date.available | 2019-11-01T07:18:42Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | ACM Transactions on Knowledge Discovery from Data, 2019, v. 13 n. 5, p. article no. 48 | - |
dc.identifier.issn | 1556-4681 | - |
dc.identifier.uri | http://hdl.handle.net/10722/279508 | - |
dc.description.abstract | We propose a Bayesian model selection (BMS) boundary detection procedure using non-local prior distributions for a sequence of data with multiple systematic mean changes. By using the non-local priors in the BMS framework, the BMS method can effectively suppress the non-boundary spike points with large instantaneous changes. Further, we speedup the algorithm by reducing the multiple change points to a series of single change point detection problems. We establish the consistency of the estimated number and locations of the change points under various prior distributions. From both theoretical and numerical perspectives, we show that the non-local inverse moment prior leads to the fastest convergence rate in identifying the true change points on the boundaries. Extensive simulation studies are conducted to compare the BMS with existing methods, and our method is illustrated with application to the magnetic resonance imaging guided radiation therapy data. | - |
dc.language | eng | - |
dc.publisher | Association for Computing Machinery, Inc. The Journal's web site is located at http://tkdd.cs.uiuc.edu | - |
dc.relation.ispartof | ACM Transactions on Knowledge Discovery from Data | - |
dc.rights | ACM Transactions on Knowledge Discovery from Data. Copyright © Association for Computing Machinery, Inc. | - |
dc.rights | ©ACM, YYYY. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in PUBLICATION, {VOL#, ISS#, (DATE)} http://doi.acm.org/10.1145/nnnnnn.nnnnnn | - |
dc.subject | Bayesian networks | - |
dc.subject | Magnetic resonance imaging | - |
dc.subject | Parallel processing systems | - |
dc.subject | Bayes factor | - |
dc.subject | Bayesian model selection | - |
dc.title | Bayesian Model Selection Approach to Multiple Change-Points Detection with Non-Local Prior Distributions | - |
dc.type | Article | - |
dc.identifier.email | Jiang, F: feijiang@hku.hk | - |
dc.identifier.email | Yin, G: gyin@hku.hk | - |
dc.identifier.authority | Jiang, F=rp02185 | - |
dc.identifier.authority | Yin, G=rp00831 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1145/3340804 | - |
dc.identifier.scopus | eid_2-s2.0-85073122477 | - |
dc.identifier.hkuros | 308619 | - |
dc.identifier.volume | 13 | - |
dc.identifier.issue | 5 | - |
dc.identifier.spage | article no. 48 | - |
dc.identifier.epage | article no. 48 | - |
dc.identifier.isi | WOS:000489839700003 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1556-4681 | - |