Mixtures of skewed Kalman filters

Handle URI:
http://hdl.handle.net/10754/563289
Title:
Mixtures of skewed Kalman filters
Authors:
Kim, Hyoungmoon; Ryu, Duchwan; Mallick, Bani K.; Genton, Marc G. ( 0000-0001-6467-2998 )
Abstract:
Normal state-space models are prevalent, but to increase the applicability of the Kalman filter, we propose mixtures of skewed, and extended skewed, Kalman filters. To do so, the closed skew-normal distribution is extended to a scale mixture class of closed skew-normal distributions. Some basic properties are derived and a class of closed skew. t distributions is obtained. Our suggested family of distributions is skewed and has heavy tails too, so it is appropriate for robust analysis. Our proposed special sequential Monte Carlo methods use a random mixture of the closed skew-normal distributions to approximate a target distribution. Hence it is possible to handle skewed and heavy tailed data simultaneously. These methods are illustrated with numerical experiments. © 2013 Elsevier Inc.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Applied Mathematics and Computational Science Program; Spatio-Temporal Statistics and Data Analysis Group
Publisher:
Elsevier BV
Journal:
Journal of Multivariate Analysis
Issue Date:
Jan-2014
DOI:
10.1016/j.jmva.2013.09.002
Type:
Article
ISSN:
0047259X
Sponsors:
This publication is based in part on work supported by Award No. KUS-C1-016-04 made by King Abdullah University of Science and Technology (KAUST), and by NSF grant DMS-1007504. The first author's research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology (2013R1A1A2005995).
Appears in Collections:
Articles; Applied Mathematics and Computational Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorKim, Hyoungmoonen
dc.contributor.authorRyu, Duchwanen
dc.contributor.authorMallick, Bani K.en
dc.contributor.authorGenton, Marc G.en
dc.date.accessioned2015-08-03T11:44:57Zen
dc.date.available2015-08-03T11:44:57Zen
dc.date.issued2014-01en
dc.identifier.issn0047259Xen
dc.identifier.doi10.1016/j.jmva.2013.09.002en
dc.identifier.urihttp://hdl.handle.net/10754/563289en
dc.description.abstractNormal state-space models are prevalent, but to increase the applicability of the Kalman filter, we propose mixtures of skewed, and extended skewed, Kalman filters. To do so, the closed skew-normal distribution is extended to a scale mixture class of closed skew-normal distributions. Some basic properties are derived and a class of closed skew. t distributions is obtained. Our suggested family of distributions is skewed and has heavy tails too, so it is appropriate for robust analysis. Our proposed special sequential Monte Carlo methods use a random mixture of the closed skew-normal distributions to approximate a target distribution. Hence it is possible to handle skewed and heavy tailed data simultaneously. These methods are illustrated with numerical experiments. © 2013 Elsevier Inc.en
dc.description.sponsorshipThis publication is based in part on work supported by Award No. KUS-C1-016-04 made by King Abdullah University of Science and Technology (KAUST), and by NSF grant DMS-1007504. The first author's research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology (2013R1A1A2005995).en
dc.publisherElsevier BVen
dc.subjectClosed skew-normal distributionen
dc.subjectClosed skew-t distributionen
dc.subjectDiscrete mixtureen
dc.subjectKalman filteren
dc.subjectScale mixturesen
dc.subjectSequential importance samplingen
dc.titleMixtures of skewed Kalman filtersen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentApplied Mathematics and Computational Science Programen
dc.contributor.departmentSpatio-Temporal Statistics and Data Analysis Groupen
dc.identifier.journalJournal of Multivariate Analysisen
dc.contributor.institutionDepartment of Applied Statistics, Konkuk University, Seoul, South Koreaen
dc.contributor.institutionDepartment of Biostatistics, Medical College of Georgia, Augusta, United Statesen
dc.contributor.institutionDepartment of Statistics, Texas A andM University, College Station, United Statesen
kaust.authorGenton, Marc G.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.