Modeling Spatial and Spatio-Temporal Non Gaussian Processes
Abstract
The ubiquitous assumption of normality for modeling spatial and spatio-temporal data can be understood for many reasons. A major one is that the multivariate normal distribution is completely characterized by its first two moments. In addition, the stability of multivariate normal distribution under summation and conditioning offers tractability and simplicity. Gaussian spatial processes are well modeled and understood by the statistical and scientific communities, but for a wide range of environmental applications Gaussian spatial or spatio-temporal models cannot reasonably be fitted to the observations.
Keywords
Covariance Function Gaussian Process Multivariate Normal Distribution Gaussian Vector Gaussian Random ProcessNotes
Acknowledgements
The author wishes to acknowledge Frédéric Baret, Sébastien Garrigues and Philippe Naveau, co-authors of some of the papers cited here. The research presented in Sect. 7.2.2 was funded by the ANR CLIMATOR project.
References
- 1.Adler, R.: The Geometry of Random Fields. Wiley, New York (1981)MATHGoogle Scholar
- 2.Adler, R., Taylor, J.: Random Fields and Geometry. Springer, Boston (2007)MATHGoogle Scholar
- 3.Allard D., Naveau, P.: A new spatial skew-normal random field model. Commun. Stat. A-Theor. 36, 1821–1834 (2007)MathSciNetMATHCrossRefGoogle Scholar
- 4.Allcroft, D., Glasbey, C.: A Latent Gaussian Markov Random-Field Model for Spatiotemporal Rainfall Disaggregation. J. Roy. Stat. Soc. C 55, 1952–2005 (2003)Google Scholar
- 5.Azzalini A., Dalla-Valle, A.: The multivariate skew-normal distribution. Biometrika 83, 715–726 (1996)MathSciNetMATHGoogle Scholar
- 6.Azzalini, A.: The skew-normal distribution and related multivariate families. Scand. J. Stat. 32, 159–188 (2005)MathSciNetMATHCrossRefGoogle Scholar
- 7.Billingsley, P.: Probability and Measure, 2nd edn. John Wiley & Sons, New York (1986)MATHGoogle Scholar
- 8.Bochner, S.: Monotone Funktionen, Stieltjessche Integrale und harmonische Analyse. Math. Ann. 108, 378–410 (1933)MathSciNetGoogle Scholar
- 9.Brisson, N., Levrault, F. (Eds.): Changement climatique, agriculture et forêt en France: simulations d’impacts sur les principales espèces. Le Livre Vert du projet CLIMATOR (2007–2010). ADEME, Orléans (2010)Google Scholar
- 10.Chilès, J.P. and Delfiner, P.: Geostatistics: modeling spatial uncertainty. John Wiley & Sons, New York (1999)Google Scholar
- 11.Cressie, N.A.C.: Statistics for Spatial Data. John Wiley & Sons, New York (1993)Google Scholar
- 12.De Oliveira, V., Kedem, B., Short, D.A.: Bayesian prediction of transformed gaussian random fields. J. Am. Stat. Assoc. 92, 1422–1433 (1997)MATHGoogle Scholar
- 13.Emery, X.: On the Existence of Mosaic and Indicator Random Fields with Spherical, Circular and Triangular Variograms. Math. Geosci. 42, 969–984 (2010)MathSciNetMATHCrossRefGoogle Scholar
- 14.Garrigues, S., Allard, D., Baret, F.: Using first and second order variograms for characterizing landscape spatial structures from remote sensing imagery. IEEE T. Geosci. Remote. 45, 1823–1834 (2007)CrossRefGoogle Scholar
- 15.Genton, M.: (Ed.) Skew-Elliptical Distributions and Their Applications. A Journey Beyond Normality. Chapman & Hall/CRC, Boca-Raton (2004)Google Scholar
- 16.Gupta, A., González-Farías, G., Domínguez-Molina, J.: A multivariate skew-normal distribution. J. Multivariate Anal. 89, 181-190 (2004)MathSciNetMATHCrossRefGoogle Scholar
- 17.Karimi, O., Mohammadzadeh, M.: Bayesian spatial regression models with closed skew normal correlated errors and missing observations. Stat. Pap. DOI 10.1007/s00362-010-0329-2 (2010)Google Scholar
- 18.Kim, H.M., Mallick, B.K.: A Bayesian prediction using the skew Gaussian distribution. J. Stat. Plan. Infer. 120, 85–101 (2004)MathSciNetMATHCrossRefGoogle Scholar
- 19.Lantuéjoul, C.: Geostatistical Simulations. Springer, Berlin (2002)Google Scholar
- 20.Matheron, G.: Effet proportionnel et lognormalité ou le retour du serpent de mer. Technical Report N-374, Centre de Géostatistique, Fontainebleau, France (1974)Google Scholar
- 21.Matheron, G.: Random Sets and Integral Geometry. Wiley, New York (1975)MATHGoogle Scholar
- 22.Matheron, G.: Suffit-il, pour une covariance, d’être de type positif ? Sciences de la Terre, Série Informatique Géologique, 26, 51–66 (1987)Google Scholar
- 23.Matheron, G.: Une conjecture sur la covariance d’un ensemble aléatoire. Cahiers de Géostatistique, Fasc. 3, 107–113. Ecole des Mines de Paris (1993)Google Scholar
- 24.Møller, J., Syversveen, A., Waagepetersen, R.: Log Gaussian Cox Processes. Scand. J. Stat. 25, 451-482 (1998)CrossRefGoogle Scholar
- 25.Myllymäki, M. and Penttinen, A.: Bayesian inference for Gaussian excursion set generated Cox processes with set marking. Stat. Comput., 20, 305–315 (2010)MathSciNetCrossRefGoogle Scholar
- 26.Naveau, P. Allard, D.: Modeling skewness in spatial data analysis without data transformation. In: Leuangthong, O., Deutsch, C., (Eds.) Proceedings of the Seventh International Geostatistics Congress, 929–938. Springer, Dordrecht (2004)Google Scholar
- 27.Porcu, E., Mateu, J., Christakos, G.: Quasi-arithmetic means of covariance functions with potential applications to space-time data. J. Multivariate Anal. 100, 1830–1844 (2009)MathSciNetMATHCrossRefGoogle Scholar
- 28.Schlather, M.: Some covariance models based on normal scale mixtures. Bernoulli 16, 780–797 (2010)MathSciNetMATHCrossRefGoogle Scholar
- 29.Schoenberg, I.J.: Metric spaces and completely montonic functions. Ann. Math. 39, 811–841 (1938)MathSciNetCrossRefGoogle Scholar
- 30.Stein, M.: Interpolation of Spatial Data: Some Theory for Kriging, New-York, Springer (1999)MATHCrossRefGoogle Scholar
- 31.Tallis, G.M.: The moment generating function of the truncated multi-normal Distribution. J. Roy. Stat. Soc. B 23, 223–229 (1961)MathSciNetMATHGoogle Scholar
- 32.Wackernagel, H.: Multivariate Geostatistics. An Introduction with Applications. 3rd Ed. Springer, Heidelberg (2003)Google Scholar
- 33.Wolpert, R. and Ickstadt, K.: Poisson/gamma random field models for spatial statistics, Biometrika, 85, 251–267 (1998)MathSciNetMATHCrossRefGoogle Scholar
- 34.Zimmerman, D.L. and Stein, M.: Classical Geostatistical Methods. In: Gelfand, A.E., Diggle, P.J., Fuentes M., Guttorp, P. (Eds.) Handbook of Spatial Statistics, 29–44. Chapman & Hall/CRC, Boca-Raton (2010)Google Scholar
- 35.Zimmerman, D.L.: Likelihood-Based Methods. In: Gelfand, A.E., Diggle, P.J., Fuentes M., Guttorp, P. (Eds.) Handbook of Spatial Statistics, 45–56. Chapman & Hall/CRC, Boca-Raton (2010)Google Scholar