Modeling space and space-time directional data using projected Gaussian processes. (English) Zbl 1368.62304
Summary: Directional data naturally arise in many scientific fields, such as oceanography (wave direction), meteorology (wind direction), and biology (animal movement direction). Our contribution is to develop a fully model-based approach to capture structured spatial dependence for modeling directional data at different spatial locations. We build a projected Gaussian spatial process, induced from an inline bivariate Gaussian spatial process. We discuss the properties of the projected Gaussian process and show how to fit this process as a model for data, using suitable latent variables, with Markov chain Monte Carlo methods. We also show how to implement spatial interpolation and conduct model comparison in this setting. Simulated examples are provided as proof of concept. A data application arises for modeling wave direction data in the Adriatic sea, off the coast of Italy. In fact, this directional data is available across time, requiring a spatio-temporal model for its analysis. We discuss and illustrate this extension.
MSC:
| 62P12 | Applications of statistics to environmental and related topics |
| 62H11 | Directional data; spatial statistics |
| 62M30 | Inference from spatial processes |
| 60G15 | Gaussian processes |
Keywords:
Bayesian kriging; bivariate Gaussian spatial processes; hierarchical model; latent variables; Markov chain Monte Carlo; separable cross-covariance functionSoftware:
spBayesReferences:
| [1] | Banerjee S., Hierarchical Modeling and Analysis for Spatial Data (2004) · Zbl 1053.62105 |
| [2] | DOI: 10.1007/978-1-4612-3688-7 · doi:10.1007/978-1-4612-3688-7 |
| [3] | DOI: 10.1016/S0167-6105(98)00011-7 · doi:10.1016/S0167-6105(98)00011-7 |
| [4] | Cressie N., Statistics for Spatio-Temporal Data (2011) · Zbl 1273.62017 |
| [5] | DOI: 10.1017/CBO9780511564345 · Zbl 0788.62047 · doi:10.1017/CBO9780511564345 |
| [6] | Fisher N.I., Journal of the Royal Statistical Society, Series B 56 pp 327– (1994) |
| [7] | DOI: 10.1198/016214502760047113 · Zbl 1073.62593 · doi:10.1198/016214502760047113 |
| [8] | DOI: 10.1198/016214506000001437 · Zbl 1284.62093 · doi:10.1198/016214506000001437 |
| [9] | DOI: 10.1256/qj.05.235 · doi:10.1256/qj.05.235 |
| [10] | DOI: 10.1142/9789812779267 · doi:10.1142/9789812779267 |
| [11] | Jammalamadaka S., Statistical Theory and Data Analysis II pp 349– (1988) |
| [12] | DOI: 10.1214/12-AOAS576 · Zbl 1257.62094 · doi:10.1214/12-AOAS576 |
| [13] | DOI: 10.1111/j.1467-9868.2010.00748.x · doi:10.1111/j.1467-9868.2010.00748.x |
| [14] | DOI: 10.1198/jasa.2009.tm08313 · Zbl 1397.60035 · doi:10.1198/jasa.2009.tm08313 |
| [15] | Kendall D.G., Journal of the Royal Statistical Society, Series B 36 pp 365– (1974) |
| [16] | Mardia K.V., Statistics of Directional Data (1972) · Zbl 0244.62005 |
| [17] | Mardia K.V., Directional Statistics (2000) · Zbl 0935.62065 |
| [18] | DOI: 10.1002/env.1133 · doi:10.1002/env.1133 |
| [19] | Morphet W.J., Simulation, Kriging, and Visualization of Circular-Spatial Data (2009) |
| [20] | DOI: 10.1080/02664760500164886 · Zbl 1121.62453 · doi:10.1080/02664760500164886 |
| [21] | DOI: 10.1177/1471082X1001100301 · doi:10.1177/1471082X1001100301 |
| [22] | DOI: 10.1080/01621459.1998.10473768 · doi:10.1080/01621459.1998.10473768 |
| [23] | DOI: 10.1007/978-1-4612-4032-7 · doi:10.1007/978-1-4612-4032-7 |
| [24] | DOI: 10.1198/016214504000000854 · Zbl 1117.62431 · doi:10.1198/016214504000000854 |
| [25] | DOI: 10.1016/j.stamet.2012.07.005 · Zbl 1365.62195 · doi:10.1016/j.stamet.2012.07.005 |
| [26] | DOI: 10.1093/biomet/67.1.255 · Zbl 0431.62056 · doi:10.1093/biomet/67.1.255 |
| [27] | DOI: 10.1016/j.jmva.2010.06.012 · Zbl 1198.62028 · doi:10.1016/j.jmva.2010.06.012 |
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.
