Probabilistic spatial prediction of categorical data using elliptical copulas

Original Paper
  • 49 Downloads

Abstract

This study uses elliptical copulas and transition probabilities for uncertainty modeling of categorical spatial data. It begins by discussing the expressions of the cumulative distribution function and probability density function of two major elliptical copulas: Gaussian copula and t copula. The basic form of spatial copula discriminant function is then derived based on Bayes’ theorem, which consists of three parts: the prior probability, the conditional marginal densities, and the conditional copula density. Finally, three kinds of parameter estimation methods are discussed, including maximum likelihood estimation, inference functions for margins and canonical maximum likelihood (CML). To avoid making assumptions on the form of marginal distributions, the CML approach is adopted in the real-world case study. Results show that the occurrence probability maps generated by these two elliptical copulas are similar to each other. However, the prediction map interpolated by Gaussian copula has a relatively higher classification accuracy than t copula.

Keywords

Gaussian copula Spatial classification t Copula Transition probability Uncertainty modeling 

Notes

Acknowledgements

This study is supported by the National Key Research and Development Program of China (No. 2016YFB0503601) and National Natural Science Foundation of China (No. 41730105). The authors are indebted to the associate editor and an anonymous reviewer for their critical review of the paper.

References

  1. Bárdossy A, Li J (2008) Geostatistical interpolation using copulas. Water Resour Res 44(7):W07412.  https://doi.org/10.1029/2007WR006115 CrossRefGoogle Scholar
  2. Bouyé E, Durrleman V, Nikeghbali A, Riboulet G, Roncalli T (2000) Copulas for finance: a reading guide and some applications. Working paper, Goupe de Recherche Opérationnelle, Crédit Lyonnais, Paris, FranceGoogle Scholar
  3. Chen X, Fan Y (2005) Pseudo-likelihood ratio tests for semiparametric multivariate copula model selection. Can J Stat 33(3):389–414CrossRefGoogle Scholar
  4. Chen SX, Huang TM (2007) Nonparametric estimation of copula functions for dependence modelling. Can J Stat 35(2):265–282CrossRefGoogle Scholar
  5. Cherubini U, Luciano E, Vecchiato W (2004) Copula methods in finance. Wiley, New YorkCrossRefGoogle Scholar
  6. Duda RO, Hart PE, Stork DG (2001) Pattern classification, 2nd edn. Wiley, New YorkGoogle Scholar
  7. Embrechts P, McNeil AJ, Straumann D (2002) Correlation and dependence in risk management: properties and pitfalls. In: Dempster M (ed) Risk management: value at risk and beyond. Cambridge University Press, New York, pp 176–223CrossRefGoogle Scholar
  8. Frahm G, Junker M, Szimayer A (2003) Elliptical copulas: applicability and limitations. Stat Probabil Lett 63(3):275–286CrossRefGoogle Scholar
  9. Frees EW, Wang P (2005) Credibility using copulas. N Am Actuar J 9(2):31–48CrossRefGoogle Scholar
  10. Genest C, Favre AC (2007) Everything you always wanted to know about copula modeling but were afraid to ask. J Hydrol Eng 12(4):347–368CrossRefGoogle Scholar
  11. Genest C, Mackay J (1986) The joy of copulas: bivariate distributions with uniform marginals. Am Stat 40(4):280–283Google Scholar
  12. Gijbels I, Mielniczuk J (1990) Estimating the density of a copula function. Commun Stat Theor Methods 19(2):445–464CrossRefGoogle Scholar
  13. Goovaerts P (1997) Geostatistics for natural resources evaluation. Oxford University Press, New YorkGoogle Scholar
  14. Górecki J, Hofert M, Holeňa M (2016) An approach to structure determination and estimation of hierarchical Archimedean copulas and its application to Bayesian classification. J Intell Inf Syst 46(1):21–59CrossRefGoogle Scholar
  15. Gräler B (2014) Modelling skewed spatial random fields through the spatial vine copula. Spat Stat 10:87–102CrossRefGoogle Scholar
  16. Gräler B, Pebesma E (2011) The pair-copula construction for spatial data: a new approach to model spatial dependency. Proc Environ Sci 7:206–211CrossRefGoogle Scholar
  17. Hennessy DA, Lapan HE (2002) The use of Archimedean copulas to model portfolio allocations. Math Finance 12(2):143–154CrossRefGoogle Scholar
  18. Huang X, Wang Z, Guo J (2016) Prediction of categorical spatial data via Bayesian updating. Int J Geogr Inf Sci 30(7):1426–1449CrossRefGoogle Scholar
  19. Huard D, Evin G, Favre AC (2006) Bayesian copula selection. Comput Stat Data Anal 51(2):809–822CrossRefGoogle Scholar
  20. Joe H (2005) Asymptotic efficiency of the two-stage estimation method for copula-based models. J Multivar Anal 94(2):401–419CrossRefGoogle Scholar
  21. Joe H, Xu JJ (1996) The estimation method of inference functions for margins for multivariate models. Techn Rep.  https://doi.org/10.14288/1.0225985 Google Scholar
  22. Journel A (2002) Combining knowledge from diverse sources: an alternative to traditional data independence hypotheses. Math Geol 34(5):573–596CrossRefGoogle Scholar
  23. Kazianka H (2013a) Approximate copula-based estimation and prediction of discrete spatial data. Stoch Environ Res Risk Assess 27(8):2015–2026CrossRefGoogle Scholar
  24. Kazianka H (2013b) spatialCopula: a Matlab toolbox for copula-based spatial analysis. Stoch Environ Res Risk Assess 27(1):121–135CrossRefGoogle Scholar
  25. Kazianka H, Pilz J (2010) Copula-based geostatistical modeling of continuous and discrete data including covariates. Stoch Environ Res Risk Assess 24(5):661–673CrossRefGoogle Scholar
  26. Kazianka H, Pilz J (2011) Bayesian spatial modeling and interpolation using copulas. Comput Geosci 37(3):310–319CrossRefGoogle Scholar
  27. Krishnan S (2008) The Tau model for data redundancy and information combination in earth sciences: theory and application. Math Geosci 40(6):705–727CrossRefGoogle Scholar
  28. Krylov VA, Moser G, Serpico SB, Zerubia J (2011) Supervised high-resolution dual-polarization SAR image classification by finite mixtures and copulas. IEEE J-STSP 5(3):554–566Google Scholar
  29. Lee LF (1983) Generalized econometric models with selectivity. Econometrica 51(2):507–512CrossRefGoogle Scholar
  30. Li W (2006) Transiogram: a spatial relationship measure for categorical data. Int J Geogr Inf Sci 20(6):693–699CrossRefGoogle Scholar
  31. Li W (2007a) A fixed-path Markov chain algorithm for conditional simulation of discrete spatial variables. Math Geol 39(2):159–176CrossRefGoogle Scholar
  32. Li W (2007b) Markov chain random fields for estimation of categorical variables. Math Geol 39(3):321–335CrossRefGoogle Scholar
  33. Li W (2007c) Transiograms for characterizing spatial variability of soil classes. Soil Sci Soc Am J 71(3):881–893CrossRefGoogle Scholar
  34. Li W, Zhang C (2005) Application of transiograms to Markov chain simulation and spatial uncertainty assessment of land-cover classes. GISci Remote Sens 42(4):297–319CrossRefGoogle Scholar
  35. Lindskog F, McNeil A, Schmock U (2003) Kendall’s tau for elliptical distributions. In: Bol G, Nakhaeizadeh G, Rachev ST, Ridder T, Vollmer K-H (eds) Credit risk. Contributions to economics. Physica-Verlag HD, Heidelberg, pp 149–156CrossRefGoogle Scholar
  36. Mashal R, Zeevi A (2002) Beyond correlation: extreme co-movements between financial assets. Technical report, Columbia UniversityGoogle Scholar
  37. Nelsen RB (2006) An introduction to copulas, 2nd edn. Springer, New YorkGoogle Scholar
  38. Okhrin O, Ristig A (2014) Hierarchical Archimedean copulae: the HAC package. J Stat Softw 58(4):1–20CrossRefGoogle Scholar
  39. Ophem HV (1999) A general method to estimate correlated discrete random variables. Economet Theory 15(2):228–237Google Scholar
  40. Patton AJ (2004) On the out-of-sample importance of skewness and asymmetric dependence for asset allocation. J Financ Econom 2(1):130–168CrossRefGoogle Scholar
  41. Polyakova EI, Journel AG (2007) The Nu expression for probabilistic data integration. Math Geol 39(8):715–733CrossRefGoogle Scholar
  42. Ranjan R, Gneiting T (2010) Combining probability forecasts. J Roy Stat Soc B 72(1):71–91.  https://doi.org/10.1111/j.1467-9868.2009.00726.x CrossRefGoogle Scholar
  43. Salinas-Gutiérrez R, Hernández-Aguirre A, Rivera-Meraz MJJ, Villa-Diharce ER (2010) Using Gaussian cpulas in supervised probabilistic classification. In: Castillo O, Kacpryzyk J, Pedrycz W (eds) Soft computing for intelligent control and mobile robotics. Springer, Berlin, pp 355–372CrossRefGoogle Scholar
  44. Sathe S (2006) A novel Bayesian classifier using copula functions. Preprint arXiv:cs/0611150
  45. Schölzel C, Friederichs P (2008) Multivariate non-normally distributed random variables in climate research-introduction to the copula approach. Nonlinear Proc Geophys 15(5):761–772CrossRefGoogle Scholar
  46. Segers J, Uyttendaele N (2014) Nonparametric estimation of the tree structure of a nested Archimedean copula. Comput Stat Data Anal 72(3):190–204CrossRefGoogle Scholar
  47. Shih JH, Louis TA (1995) Inferences on the association parameter in copula models for bivariate survival data. Biometrics 51(4):1384–1399CrossRefGoogle Scholar
  48. Silva RDS, Lopes HF (2008) Copula, marginal distributions and model selection: a Bayesian note. Stat Comput 18(3):313–320CrossRefGoogle Scholar
  49. Sklar A (1959) Fonctions de répartition à n dimensions et leurs marges. Publ Inst Stat Univ Paris 8(1):229–231Google Scholar
  50. Trivedi PK, Zimmer DM (2005) Copula modeling: an introduction for practitioners. Found Trends Econom 1(1):1–111CrossRefGoogle Scholar
  51. Voisin A, Krylov VA, Moser G, Serpico SB, Zerubia J (2014) Supervised classification of multisensor and multiresolution remote sensing images with a hierarchical copula-based approach. IEEE Trans Geosci Remote Sens 52(6):3346–3358CrossRefGoogle Scholar
  52. Yan J (2007) Enjoy the joy of copulas: with a package copula. J Stat Softw 21(4):1–21CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany 2017

Authors and Affiliations

  1. 1.Data Center (Beijing)Agricultural Bank of ChinaBeijingChina
  2. 2.Department of StatisticsCentral South UniversityChangshaChina

Personalised recommendations