Spatial Expectile Predictions for Elliptical Random Fields

  • V. Maume-Deschamps
  • D. Rullière
  • A. Usseglio-Carleve


In this work, we consider an elliptical random field. We propose some spatial expectile predictions at one site given observations of the field at some other locations. To this aim, we first give exact expressions for conditional expectiles, and discuss problems that occur for computing these values. A first affine expectile regression predictor is detailed, an explicit iterative algorithm is obtained, and its distribution is given. Direct simple expressions are derived for some particular elliptical random fields. The performance of this expectile regression is shown to be very poor for extremal expectile levels, so that a second predictor is proposed. We prove that this new extremal prediction is asymptotically equivalent to the true conditional expectile. We also provide some numerical illustrations, and conclude that Expectile Regression may perform poorly when one leaves the Gaussian random field setting.


Elliptical distribution Expectile regression Extremal expectile Spatial prediction Kriging 

Mathematics Subject Classification (2010)

60G15 60G60 62H11 62M30 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.



The authors thank the referee for his comments and suggestions that really helped to improve the paper. We are also grateful to the Editor-in-Chief, Joseph Glaz, for cordial exchanges. This work was supported by the LABEX MILYON (ANR-10-LABX-0070) of Université de Lyon, within the program “Investissements d’Avenir” (ANR-11-IDEX-0007) operated by the French National Research Agency (ANR).


  1. Abramowitz M, Stegun IA et al (1966) Handbook of mathematical functions. Applied Mathematics Series 55:62Google Scholar
  2. Bellini F, Klar B, Müller A, Rosazza Gianin E (2014) Generalized quantiles as risk measures. Insurance: Mathematics and Economics 54:41–48MathSciNetzbMATHGoogle Scholar
  3. Cambanis S, Huang S, Simons G (1981) On the theory of elliptically contoured distributions. J Multivar Anal 11:368–385MathSciNetCrossRefzbMATHGoogle Scholar
  4. Djurčić D, Torgašev A (2001) Strong asymptotic equivalence and inversion of functions in the class K c. J Math Anal Appl 255:383–390MathSciNetCrossRefzbMATHGoogle Scholar
  5. Eltoft T, Kim T, Lee T-W (2006) On the multivariate Laplace distribution. IEEE Signal Process Lett 13(5):300–303CrossRefGoogle Scholar
  6. Frahm G (2004) Generalized elliptical distributions: theory and applications. PhD thesis, Universität zu KölnGoogle Scholar
  7. Fraley C, Raftery A (2002) Model-based clustering, discriminant analysis, and density estimation. J Am Stat Assoc 97(458):611–630MathSciNetCrossRefzbMATHGoogle Scholar
  8. Frontini M, Sormani E (2003) Some variant of Newton’s method with third-order convergence. Appl Math Comput 140:419–426MathSciNetzbMATHGoogle Scholar
  9. Gómez HW, Quintana FA, Torres FJ (2007) A new family of slash-distributions with elliptical contours. Statistics & Probability Letters 77:717–725MathSciNetCrossRefzbMATHGoogle Scholar
  10. Hult H, Lindskog F (2002) Multivariate extremes, aggregation and dependence in elliptical distributions. Adv Appl Probab 34(3):587–608MathSciNetCrossRefzbMATHGoogle Scholar
  11. Hunter D, Lange K (2004) A tutorial on MM algorithms. Am Stat 58(1):30–37MathSciNetCrossRefGoogle Scholar
  12. Jones M (1994) Expectiles and M-quantiles are quantiles. Statistics & Probability Letters 20(2):149–153MathSciNetCrossRefzbMATHGoogle Scholar
  13. Kano Y (1994) Consistency property of elliptical probability density functions. J Multivar Anal 51:139–147MathSciNetCrossRefzbMATHGoogle Scholar
  14. Koenker R, Bassett GJ (1978) Regression quantiles. Econometrica 46(1):33–50MathSciNetCrossRefzbMATHGoogle Scholar
  15. Kozubowski T, Podgórskib K, Rychlik I (2013) Multivariate generalized Laplace distribution and related random fields. J Multivar Anal 113:59–72MathSciNetCrossRefzbMATHGoogle Scholar
  16. Krige D (1951) A statistical approach to some basic mine valuation problems on the witwatersrand. J Chem Metall Min Soc 52:119–139Google Scholar
  17. Ligas M, Kulczycki M (2010) Simple spatial prediction by least squares prediction, simple kriging, and conditional expectation of normal vector. Geodasy and Cartography 59(2):69–81Google Scholar
  18. Matheron G (1963) Traité de géostatistique appliquée. Bureau de recherches géologiques et minières (France)Google Scholar
  19. Maume-Deschamps V, Rullière D, Usseglio-Carleve A (2017) Quantile predictions for elliptical random fields. J Multivar Anal 159:1–17MathSciNetCrossRefzbMATHGoogle Scholar
  20. Nadarajah S (2003) The Kotz type distribution with applications. Statistics 37 (4):341–358MathSciNetCrossRefzbMATHGoogle Scholar
  21. Nadarajah S, Kotz S (2004) Multivariate t-distributions and their applications. Cambridge University PressGoogle Scholar
  22. Newey W, Powell J (1987) Asymmetric least squares estimation and testing. Econometrica 55:819–847MathSciNetCrossRefzbMATHGoogle Scholar
  23. Sobotka F, Kneib T (2012) Geoadditive expectile regression. Comput Stat Data Anal 56:755–767MathSciNetCrossRefzbMATHGoogle Scholar
  24. Taylor JW (2008) Estimating value at risk and expected shortfall using expectiles. J Financ Economet 6(2):231–252CrossRefGoogle Scholar
  25. Wang Y, Wang S, Lai KK (2011) Measuring financial risk with generalized asymmetric least squares regression. Appl Soft Comput 11(8):5793–5800MathSciNetCrossRefGoogle Scholar
  26. Yang Y, Zhang T, Zou H (2017) Flexible expectile regression in reproducing Kernel Hilbert spaces. Technometrics. doi: 10.1080/00401706.2017.1291450
  27. Ziegel J (2016) Mathematical Finance 26(4):901–918Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  • V. Maume-Deschamps
    • 1
  • D. Rullière
    • 2
  • A. Usseglio-Carleve
    • 1
  1. 1.Institut Camille Jordan ICJ UMR 5208 CNRSUniversité de Lyon, Université Lyon 1VilleurbanneFrance
  2. 2.Laboratoire SAF EA2429Université de Lyon, Université Lyon 1VilleurbanneFrance

Personalised recommendations