Tukey g-and-h Random Fields

Handle URI:
http://hdl.handle.net/10754/622962
Title:
Tukey g-and-h Random Fields
Authors:
Xu, Ganggang; Genton, Marc G. ( 0000-0001-6467-2998 )
Abstract:
We propose a new class of trans-Gaussian random fields named Tukey g-and-h (TGH) random fields to model non-Gaussian spatial data. The proposed TGH random fields have extremely flexible marginal distributions, possibly skewed and/or heavy-tailed, and, therefore, have a wide range of applications. The special formulation of the TGH random field enables an automatic search for the most suitable transformation for the dataset of interest while estimating model parameters. Asymptotic properties of the maximum likelihood estimator and the probabilistic properties of the TGH random fields are investigated. An efficient estimation procedure, based on maximum approximated likelihood, is proposed and an extreme spatial outlier detection algorithm is formulated. Kriging and probabilistic prediction with TGH random fields are developed along with prediction confidence intervals. The predictive performance of TGH random fields is demonstrated through extensive simulation studies and an application to a dataset of total precipitation in the south east of the United States.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
Xu G, Genton MG (2016) Tukey g-and-h Random Fields. Journal of the American Statistical Association: 0–0. Available: http://dx.doi.org/10.1080/01621459.2016.1205501.
Publisher:
Informa UK Limited
Journal:
Journal of the American Statistical Association
Issue Date:
15-Jul-2016
DOI:
10.1080/01621459.2016.1205501
Type:
Article
ISSN:
0162-1459; 1537-274X
Is Supplemented By:
Ganggang Xu, & Genton, M. G. (2016). Tukey g-and-h Random Fields. Figshare. https://doi.org/10.6084/m9.figshare.3487658; DOI:10.6084/m9.figshare.3487658; HANDLE:http://hdl.handle.net/10754/624776
Additional Links:
http://www.tandfonline.com/doi/full/10.1080/01621459.2016.1205501
Appears in Collections:
Articles; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorXu, Ganggangen
dc.contributor.authorGenton, Marc G.en
dc.date.accessioned2017-03-05T06:13:15Z-
dc.date.available2017-03-05T06:13:15Z-
dc.date.issued2016-07-15en
dc.identifier.citationXu G, Genton MG (2016) Tukey g-and-h Random Fields. Journal of the American Statistical Association: 0–0. Available: http://dx.doi.org/10.1080/01621459.2016.1205501.en
dc.identifier.issn0162-1459en
dc.identifier.issn1537-274Xen
dc.identifier.doi10.1080/01621459.2016.1205501en
dc.identifier.urihttp://hdl.handle.net/10754/622962-
dc.description.abstractWe propose a new class of trans-Gaussian random fields named Tukey g-and-h (TGH) random fields to model non-Gaussian spatial data. The proposed TGH random fields have extremely flexible marginal distributions, possibly skewed and/or heavy-tailed, and, therefore, have a wide range of applications. The special formulation of the TGH random field enables an automatic search for the most suitable transformation for the dataset of interest while estimating model parameters. Asymptotic properties of the maximum likelihood estimator and the probabilistic properties of the TGH random fields are investigated. An efficient estimation procedure, based on maximum approximated likelihood, is proposed and an extreme spatial outlier detection algorithm is formulated. Kriging and probabilistic prediction with TGH random fields are developed along with prediction confidence intervals. The predictive performance of TGH random fields is demonstrated through extensive simulation studies and an application to a dataset of total precipitation in the south east of the United States.en
dc.publisherInforma UK Limiteden
dc.relation.urlhttp://www.tandfonline.com/doi/full/10.1080/01621459.2016.1205501en
dc.rightsThis is an Accepted Manuscript of an article published by Taylor & Francis in Journal of the American Statistical Association on 15 Jul 2016, available online: http://wwww.tandfonline.com/10.1080/01621459.2016.1205501.en
dc.subjectContinuous Rank Probability Scoreen
dc.subjectHeavy tailsen
dc.subjectKrigingen
dc.subjectLog-Gaussian random fielden
dc.subjectNon-Gaussian random fielden
dc.subjectPITen
dc.subjectProbabilistic predictionen
dc.subjectSkewnessen
dc.subjectSpatial outliersen
dc.subjectSpatial statisticsen
dc.subjectTukey g-and-h distributionen
dc.titleTukey g-and-h Random Fieldsen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalJournal of the American Statistical Associationen
dc.eprint.versionPost-printen
dc.contributor.institutionDepartment of Mathematical Sciences, Binghamton University, Binghamton, NY 13902, USAen
kaust.authorGenton, Marc G.en
dc.relation.isSupplementedByGanggang Xu, & Genton, M. G. (2016). Tukey g-and-h Random Fields. Figshare. https://doi.org/10.6084/m9.figshare.3487658en
dc.relation.isSupplementedByDOI:10.6084/m9.figshare.3487658en
dc.relation.isSupplementedByHANDLE:http://hdl.handle.net/10754/624776en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.