A class of convolution-based models for spatio-temporal processes with non-separable covariance structure. (English) Zbl 1349.62449
Summary: We propose a new parametric family of models for real-valued spatio-temporal stochastic processes \(S(x, t)\) and show how low-rank approximations can be used to overcome the computational problems that arise in fitting the proposed class of models to large datasets. Separable covariance models, in which the spatio-temporal covariance function of \(S(x, t)\) factorizes into a product of purely spatial and purely temporal functions, are often used as a convenient working assumption but are too inflexible to cover the range of covariance structures encountered in applications. We define positive and negative non-separability and show that in our proposed family we can capture positive, zero and negative non-separability by varying the value of a single parameter.
MSC:
| 62M30 | Inference from spatial processes |
References:
| [1] | Banerjee, Gaussian predictive process models for large spatial data sets, J. Roy. Statist. Soc. Ser. B 70 pp 825– (2008) · Zbl 1533.62065 |
| [2] | Barry, Blackbox Kriging: spatial prediction without specifying variogram models, J. Agric. Biol. Environ. Stat. 1 pp 297– (1996) |
| [3] | Bochner, Harmonic analysis and the theory of probability (1955) |
| [4] | Brown, Blur-generated non-separable space-time models, J. Roy. Statist. Soc. Ser. B 62 pp 847– (2000) · Zbl 0957.62081 |
| [5] | Brown, Space-time calibration of a radar rainfall data, Appl. Statist. 50 pp 221– (2001) |
| [6] | Calder, Case studies in Bayesian statistics. Volume VI pp 165– (2002) · doi:10.1007/978-1-4612-2078-7_6 |
| [7] | Calder, Dynamic factor process convolution models for multivariate space-time data with application to air quality assessment, Environ. Ecol. Stat. 14 pp 229– (2007) |
| [8] | Calder, Proceedings of the 56th Session of the International Statistical Institute. (2007) |
| [9] | Champeney, A handbook of Fourier theorems (1987) · Zbl 0632.42001 · doi:10.1017/CBO9781139171823 |
| [10] | Cox, Some statistical methods connected with series of events, J. Roy. Statist. Soc. Ser. B 17 pp 129– (1955) · Zbl 0067.37403 |
| [11] | Crainiceanu, Bivariate binomial spatial modeling of Loa loa prevalence in tropical Africa, J. Amer. Statist. Assoc. 103 pp 21– (2008) · Zbl 1469.86015 |
| [12] | Cressie, Statistics for spatial data (1993) |
| [13] | Cressie, Classes of nonseparable, spatiotemporal stationary covariance functions, J. Amer. Statist. Assoc. 94 pp 1330– (1998) |
| [14] | Cressie, Fixed rank Kriging for very large data sets, J. Roy. Statist. Soc. Ser. B 70 pp 209– (2008) · Zbl 05563351 |
| [15] | De Cesare, Estimating and modeling space-time correlation structures, Statist. Probab. Lett. 51 pp 9– (2001) · Zbl 1036.62095 |
| [16] | De Iaco, Space-time analysis using a general product-sum model, Appl. Statist. 50 pp 221– (2001) · Zbl 1129.62413 |
| [17] | Diggle, Model-based geostatistics (2007) |
| [18] | Diggle, Point process methodology for on-line spatio-temporal disease surveillance, Environmetrics 16 pp 423– (2005) |
| [19] | Fuentes, Spectral methods for nonstationary spatial processes, Biometrika 89 pp 197– (2002) · Zbl 0997.62073 |
| [20] | Ganguli, SemiPar 1.0 users’ manual (2005) |
| [21] | Gneiting, Nonseparable, stationary covariance functions for space-time data, J. Amer. Statist. Assoc. 97 pp 590– (2002) · Zbl 1073.62593 |
| [22] | Higdon, A process-convolution approach to modeling temperatures in the North Atlantic Ocean, J. Environ. Ecol. Stat. 5 pp 173– (1998) |
| [23] | Higdon, Quantitative methods for current environmental issues pp 37– (2002) · doi:10.1007/978-1-4471-0657-9_2 |
| [24] | Higdon, Bayesian statistics 6. Proceedings of the Sixth Valencia International Meeting pp 761– (1999) |
| [25] | Kaufman, Finding groups in data: an introduction to cluster analysis (1990) · Zbl 1345.62009 |
| [26] | Kern, Bayesian process-convolution approaches to specifying spatial dependence structure (2000) |
| [27] | Lee, Efficient models for correlated data via convolutions of intrinsic processes, Statist. Model. 5 pp 53– (2005) · Zbl 1071.62089 |
| [28] | Ma, Families of spatio-temporal stationary covariance models, J. Statist. Plann. Inference 116 pp 489– (2003) · Zbl 1043.62051 |
| [29] | Majumdar, Multivariate spatial modeling for geostatistical data using convolved covariance functions, Math. Geol. 39 pp 225– (2007) · Zbl 1126.86007 |
| [30] | Mitchell, Testing for separability of space-time covariances, Environmetrics 16 pp 819– (2005) |
| [31] | Møller, Log Gaussian Cox process, Scand. J. Statist. 25 pp 451– (1998) |
| [32] | Nychka, Case studies in environmental statistics (1998) · Zbl 0899.00022 · doi:10.1007/978-1-4612-2226-2 |
| [33] | Oliver, Gaussian cosimulation: modelling of the cross-covariance, Math. Geol. 35 pp 681– (2003) · Zbl 1047.86010 |
| [34] | Stein, Space-time covariance functions, J. Amer. Statist. Assoc. 100 pp 310– (2005) · Zbl 1117.62431 |
| [35] | Ver Hoef, Constructing and fitting models for cokriging and multivariable spatial prediction, J. Statist. Plann. Inference 69 pp 275– (1998) · Zbl 0935.62110 |
| [36] | Wackernagel, Multivariate geostatistics (2003) · doi:10.1007/978-3-662-05294-5 |
| [37] | Yaglom, Correlation theory of stationary and related random functions (1987) · Zbl 0685.62078 · doi:10.1007/978-1-4612-4628-2 |
| [38] | Yaglom, An introduction to the theory of stationary random functions (2004) |
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. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
