×

zbMATH — the first resource for mathematics

Likelihood-based inference for multivariate space-time wrapped-Gaussian fields. (English) Zbl 07184753
Summary: Directional spatial data, typically represented through angles, are of central importance in many scientific disciplines, such as environmental sciences, oceanography and meteorology, among others. We propose a wrapped-Gaussian field to model directions in a multivariate spatial or spatio-temporal context. The \(n\)-dimensional distributions of a wrapped Gaussian field can be written as a sum over the \(n\)-dimensional lattice of \(\mathbb{R}^n\), making likelihood-based inference impracticable. We adopt a parametric approach and develop composite likelihood methods to estimate the parameters associated with location, as well as the spatial or spatio-temporal dependence. Our approach outperforms the analytical and computational limitations of full likelihood, because it works with the marginal bivariate distributions of the random field. We study the performance of the method through simulation experiments and by analysing a real data set of wave directions from the Adriatic coast of Italy.
MSC:
62-XX Statistics
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] Mardia KV. Statistics of directional data. J R Statist Soc Ser B (Methodol). 1975;37(3):349-393. [Google Scholar] · Zbl 0314.62026
[2] Fisher N. Statistical analysis of circular data. Statistical analysis of circular data. Cambridge: Cambridge University Press; 1995. [Google Scholar] · Zbl 0788.62047
[3] Jammalamadaka S, Sengupta A. Topics in circular statistics. Series on multivariate analysis. Singapore: World Scientific; 2001. [Crossref], [Google Scholar]
[4] Coles S. Inference for circular distributions and processes. Stat Comput. 1998;8(2):105-113. doi: 10.1023/A:1008930032595[Crossref], [Web of Science ®], [Google Scholar]
[5] Abramowitz M, Stegun IA editors. Handbook of mathematical functions. New York: Dover; 1970. [Google Scholar] · Zbl 0171.38503
[6] Mardia KV, Hughes G, Taylor CC, Singh H. A multivariate Von-Mises distribution with applications to bioinformatics. Canad J Stat / La Revue Canadienne de Statistique. 2008;36(1):99-109. doi: 10.1002/cjs.5550360110[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1143.62031
[7] Wang F, Gelfand AE. Modeling space and space-time directional data using projected gaussian processes. J Am Statist Assoc. 2014;109(508):1565-1580. doi: 10.1080/01621459.2014.934454[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1368.62304
[8] Jona-Lasinio G, Gelfand A, Jona-Lasinio M. Spatial analysis of wave direction data using wrapped gaussian processes. Ann Appl Stat. 2012;6(4):1478-1498. doi: 10.1214/12-AOAS576[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1257.62094
[9] Mastrantonio G, Jona Lasinio G, Gelfand A. Spatio-temporal circular models with non-separable covariance structure. Test; 2015. [Web of Science ®], [Google Scholar] · Zbl 1402.62102
[10] Wang F, Gelfand AE, Jona-Lasinio G. Joint spatio-temporal analysis of a linear and a directional variable: space-time modeling of wave heights and wave directions in the adriatic sea. Stat Sin. 2015;25:25-39. [Web of Science ®], [Google Scholar] · Zbl 06497332
[11] Mastrantonio G, Gelfand A, Jona Lasinio G. The wrapped skew gaussian process for analyzing spatio-temporal data. Stoch Environ Res Risk Assess; 2015. [Google Scholar]
[12] Cox D, Reid N. Miscellanea: A note on pseudolikelihood constructed from marginal densities. Biometrika. 2004;91:729-37. doi: 10.1093/biomet/91.3.729[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1162.62365
[13] Lindsay B. Composite likelihood methods. Contemp Math. 1988;80:221-239. doi: 10.1090/conm/080/999014[Crossref], [Google Scholar]
[14] Varin C, Reid N, Firth D. An overview of composite likelihood methods. Statist Sin. 2011;21:5-42. [Web of Science ®], [Google Scholar] · Zbl 05849508
[15] Bevilacqua M, Gaetan C. Comparing composite likelihood methods based on pairs for spatial gaussian random fields. Stat Comput. 2014;1-16. [Google Scholar] · Zbl 1332.62368
[16] Bevilacqua M, Gaetan C, Mateu J, Porcu E. Estimating space and space-time covariance functions for large data sets: a weighted composite likelihood approach. J Am Statist Assoc. 2012;107:268-280. doi: 10.1080/01621459.2011.646928[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1261.62088
[17] Curriero FC, Lele S. A composite likelihood approach to semivariogram estimation. J Agric Biol Environ Stat. 1999;4:9-28. doi: 10.2307/1400419[Crossref], [Web of Science ®], [Google Scholar]
[18] Bevilacqua M, Alegria A, Velandia D, Porcu E. Composite likelihood for multivariate Gaussian random fields, 2015, Submitted. [Google Scholar] · Zbl 1347.62237
[19] Padoan SA, Ribatet M, Sisson S. Likelihood-based inference for max-stable processes. J Am Statist Assoc. 2010;105:263-277. doi: 10.1198/jasa.2009.tm08577[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1397.62172
[20] Sang H, Genton MG. Tapered composite likelihood for spatial max-stable models. Spatial Stat. 2014;8:86-103. doi: 10.1016/j.spasta.2013.07.003[Crossref], [Web of Science ®], [Google Scholar]
[21] Heagerty PJ, Lele SR. A composite likelihood approach to binary spatial data. J Am Statist Assoc. 1998;93:1099-1111. doi: 10.1080/01621459.1998.10473771[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1064.62528
[22] Genton M, Kleiber W. Cross-covariance functions for multivariate geostatistics. Statist Sci. 2015;30(2):147-163. doi: 10.1214/14-STS487[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1332.86010
[23] Bevilacqua M, Hering AS, Porcu E. On the flexibility of multivariate covariance models: comment on the paper by genton and kleiber. Statist Sci. 2015;30(2):167-169. doi: 10.1214/15-STS516[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1332.86006
[24] Mardia KV, Goodall C. Spatial-temporal analysis of multivariate environmental monitoring data. Multivariate Environ Stat. 1993;6(76):347-385. [Google Scholar] · Zbl 0825.62996
[25] Wackernagel H. Multivariate geostatistics: an introduction with applications. 3rd ed.New York: Springer; 2003. [Crossref], [Google Scholar] · Zbl 1015.62128
[26] Gneiting T, Kleiber W, Schlather M. Matérn Cross-Covariance functions for multivariate random fields. J Am Statist Assoc. 2010;105:1167-1177. doi: 10.1198/jasa.2010.tm09420[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1390.62194
[27] Porcu E, Daley D, Buhmann M, Bevilacqua M. Radial basis functions with compact support for multivariate geostatistics. Stoch Environ Res Risk Assess. 2013;27(4):909-922. doi: 10.1007/s00477-012-0656-z[Crossref], [Web of Science ®], [Google Scholar]
[28] Daley DJ, Porcu E, Bevilacqua M. Classes of compactly supported covariance functions for multivariate random fields. Stoch Environ Res Risk Assess. 2015;29(4):1249-1263. doi: 10.1007/s00477-014-0996-y[Crossref], [Web of Science ®], [Google Scholar]
[29] Gneiting T. Stationary covariance functions for space-time data. J Am Statist Assoc. 2002;97:590-600. doi: 10.1198/016214502760047113[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1073.62593
[30] Zastavnyi VP, Porcu E. Characterization theorems for the gneiting class of space-time covariances. Bernoulli. 2011;17(1):456-465. doi: 10.3150/10-BEJ278[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1284.62592
[31] Stein M. Interpolation of spatial data. Some theory of Kriging. New York: Springer; 1999. [Crossref], [Google Scholar] · Zbl 0924.62100
[32] Furrer R, Genton MG, Nychka D. Covariance tapering for interpolation of large spatial datasets. J Comput Graph Stat. 2006;15:502-523. doi: 10.1198/106186006X132178[Taylor & Francis Online], [Web of Science ®], [Google Scholar]
[33] Kaufman CG, Schervish MJ, Nychka DW. Covariance tapering for likelihood-based estimation in large spatial data sets. J Am Statist Assoc. 2008;103:1545-1555. doi: 10.1198/016214508000000959[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1286.62072
[34] Guyon X. Random fields on a network. New York: Springer; 1995. [Google Scholar] · Zbl 0839.60003
[35] Godambe V. Estimating functions. New York: Oxford University Press; 1991. [Google Scholar] · Zbl 0745.00006
[36] Padoan S, Bevilacqua M. Analysis of random fields using CompRandfld. J Statist Softw. 2015;63(1):1-27. [Google Scholar]
[37] Banerjee S. On geodetic distance computations in spatial modeling. Biometrics. 2005;61(2):617-625. doi: 10.1111/j.1541-0420.2005.00320.x[Crossref], [PubMed], [Web of Science ®], [Google Scholar]
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.