Anisotropic Matern correlation and spatial prediction using REML

Simple item page
dc.contributor.authorHaskard, K.
dc.contributor.authorCullis, B.
dc.contributor.authorVerbyla, A.
dc.date.issued2007
dc.description.abstractThe Matérn correlation function provides great flexibility for modeling spatially correlated random processes in two dimensions, in particular via a smoothness parameter, whose estimation allows data to determine the degree of smoothness of a spatial process. The extension to include anisotropy provides a very general and flexible class of spatial covariance functions that can be used in a model-based approach to geostatistics, in which parameter estimation is achieved via REML and prediction is within the E-BLUP framework. In this article we develop a general class of linear mixed models using an anisotropic Matérn class with an extended metric. The approach is illustrated by application to soil salinity data in a rice-growing field in Australia, and to fine-scale soil pH data. It is found that anisotropy is an important aspect of both datasets, emphasizing the value of a straightforward and accessible approach to modeling anisotropy. © 2007 American Statistical Association and the International Biometric Society.
dc.identifier.citationJournal of Agricultural, Biological, and Environmental Statistics, 2007; 12(2):147-160
dc.identifier.doi10.1198/108571107X196004
dc.identifier.issn1085-7117
dc.identifier.issn1537-2693
dc.identifier.urihttp://hdl.handle.net/2440/43957
dc.language.isoen
dc.publisherAmer Statistical Assoc & International Biometric Soc
dc.source.urihttps://doi.org/10.1198/108571107x196004
dc.subjectGeometric anisotropy
dc.subjectKriging
dc.subjectModel-based geostatistics
dc.subjectResidual maximum likelihood
dc.subjectSpatial correlation
dc.titleAnisotropic Matern correlation and spatial prediction using REML
dc.typeJournal article
pubs.publication-statusPublished

Files

Collections

Agriculture, Food and Wine publications