Skip to main navigation menu Skip to main content Skip to site footer

Vol. 13 No. 2 (2022)
Vol. 13 Núm. 2 (2022): Vol. 13 Núm. 2 (2022): Vol 13, Núm.2 (2022): Julio-Diciembre

Revisiones/Reviews

Testing for Normality in Geostatistics. A New Approach Based on the Mahalanobis Distance

https://doi.org/10.19053/01217488.v13.n2.2022.13650

Published 2022-07-12

  • Ramón Giraldo
    • ,
  • Emilio Porcu

Ramón Giraldo
a:1:{s:5:"es_ES";s:46:"Universidad Nacional de Colombia, Sede Bogotá";}

Emilio Porcu
Khalifa University, Abu Dabi

Abstract

Simple kriging is a best linear predictor (BLP) and ordinary kriging is a best linear unbiased predictor (BLUP). When the underlying process is normal, simple kriging is not only a BLP but a best predictor (BT) as well, that is, under squared loss, this predictor coincides with the conditional expectation of the predictor given the information. In this scenario, ordinary kriging provides an approximation to the BP. For this reason, in applied geostatistics, it is important to test for normality. Given a realization of a spatial random process, the simple kriging predictor will be optimal if the random vector follows a multivariate normal distribution. Some classical tests, such as Shapiro-Wilk (SW), Shapiro-Francia (SF), or Anderson-Darling (AD) are frequently used to evaluate the normality assumption. Such approaches assume independence and hence are not effective for at least two reasons. On the one hand, observations in a geostatistical analysis are typically spatially correlated. On the other hand, kriging optimality as mentioned above is based on multivariate rather than univariate normality. In this work, we provide a simulation study to describe the negative effect of using normality univariate tests with geostatistical data. We also show how the Mahalanobis distance can be adapted to the geostatistical context to test for normality.

Keywords

Chi-square distribution, Multivariate normal distribution, Mahalanobis distance, Normality test, Random field, Monte Carlo simulation.

PDF (Español)

References

  1. G. Robertson. “Geostatistics in ecology: interpolating with known variance ”. Ecology, vol. 68, no. 3, pp 744-748, 1987. DOI: https://doi.org/10.2307/1938482
  2. T. Hooks, D. Marx, S. Kachman, J. Pedersen, R. Eigenberg, R. “Analysis of covariance with spatially correlated secondary variables ”. Revista Colombiana de Estadística, vol. 31, no. 1, pp. 95-109, 2008.
  3. G. Severino, M. Scarfato, G. Toraldo. “Mining geostatistics to quantify the spatial variability of certain soil flow properties ”. Procedia Computer Science, vol. 98, 419-424, 2016. DOI: https://doi.org/10.1016/j.procs.2016.09.064
  4. I. Gundogdu. “Usage of multivariate geostatistics in interpolation processes for meteorological precipitation maps ”. Theoretical and Applied Climatology, vol. 127, no. 1-2, 81-86, 2017. DOI: https://doi.org/10.1007/s00704-015-1619-3
  5. R. Giraldo, L. Herrera, V. Leiva. “Cokriging prediction using as secondary variable a functional random field with application in environmental pollution ”. Mathematics, vol. 8, no.8, 1305, 2020. DOI: https://doi.org/10.3390/math8081305
  6. M. Oliver, R. Webster. Basic steps in geostatistics: The variogram and kriging. Springer. 2015. DOI: https://doi.org/10.1007/978-3-319-15865-5
  7. E. Lehmann, G. Casella. Theory of Point Estimation. Springer-Verlag, 1998.
  8. J. Chiles, P. Delfiner. Geostatistics: Modeling Spatial Uncertainty. John Wiley & Sons, 1999. DOI: https://doi.org/10.1002/9780470316993
  9. O. Schabenberger, C. Gotway. Statistical Methods for Spatial Data Analysis. Chapman & Hall, 2005.
  10. D. McGratha, C. Zhangb, O. Cartona. “Geostatistical analysis and hazard assessment on soil lead in silvermines area, Ireland ”. Environmental Pollution, vol. 127, 239-248, 2004. DOI: https://doi.org/10.1016/j.envpol.2003.07.002
  11. V. Júnior, M. Carvalho, J. Dafonte, O. Freddi, E. Vidal, O. Ingaramoc. “Spatial variability of soil water content and mechanical resistance of Brazilian ferralsol ”. Soil & Tillage Research, vol. 85, 166-177, 2006. DOI: https://doi.org/10.1016/j.still.2005.01.018
  12. A. Dexter, A. Czyz, O. Gate. “A method for prediction of soil penetration resistance ”. Soil & Tillage Research, vol. 93, 412-419, 2007. DOI: https://doi.org/10.1016/j.still.2006.05.011
  13. K. Kamarudin, M. Tomita M, K. Kondo, S. Abe. “Geostatistical estimation of surface soil carbon stock in Mt. Wakakusa grassland of Japan ”. Landscape and Ecological Engineering, vol. 15, no.2, 215-221, 2019. DOI: https://doi.org/10.1007/s11355-019-00370-1
  14. J. Iqbal, J. Thomasson, J. Jenkins, P. Owens, Whisler, F. “Spatial variability analysis of soil physical properties of alluvial soils ”. Soil Science Society of America Journal, vol. 69, 1338-1350, 2005. DOI: https://doi.org/10.2136/sssaj2004.0154
  15. L. Pozdnyakova, D. Giménez, P. Oudemans. “Spatial analysis of cranberry yield at three scales ”.Agronomy Journal, vol. 97, 49-57, 2005. DOI: https://doi.org/10.2134/agronj2005.0049
  16. M. Carrara, A. Castrignano, A. Comparetti, P. Febo, S. Orlando. “Mapping of Penetrometer Resistance in Relation to Tractor Traffic Using Multivariate Geostatistics ”. Geoderma, vol. 142, 294-307, 2007. DOI: https://doi.org/10.1016/j.geoderma.2007.08.020
  17. J. Lima, S. Silva. “Multivariate analysis and geostatistics of the fertility of a humic rhodic hapludox under coffee cultivation ”. Revista Brasileira de Ciencia do Solo, vol. 36, no. 2, 467-474, 2012. DOI: https://doi.org/10.1590/S0100-06832012000200016
  18. E. Barca, D. De Benedetto, A. Stellaccic. “Contribution of EMI and GPR proximal sensing data in soil water content assessment by using linear mixed effects models and geostatistical approaches ”. Geoderma, vol. 343, no. 1, 280-293, 2019. DOI: https://doi.org/10.1016/j.geoderma.2019.01.030
  19. E. Pardo-Igúzquiza, P. Dowd. “Normality tests for spatially correlated data ”. Mathematical Geology, vol. 36, no. 6, 659-681, 2004. DOI: https://doi.org/10.1023/B:MATG.0000039540.43774.2b
  20. R. Olea, V. Pavlosky. “Kolmogorov-Smirnov test for spatially correlated data ”. Stochastic Environmental Research and Risk Assessment, vol. 23, no.6, 749-757, 2008. DOI: https://doi.org/10.1007/s00477-008-0255-1
  21. K. Mardia. “Measures of multivariate skewness and kurtosis with applications ”. Biometrika. vol. 57, no. 3, 519-530, 1970. DOI: https://doi.org/10.1093/biomet/57.3.519
  22. G.Szekely, M. Rizzo. “A new test for multivariate normality ”. Journal of Multivariate Analysis. vol. 93, 58-80, 2005. DOI: https://doi.org/10.1016/j.jmva.2003.12.002
  23. T. Anderson. An Introduction to Multivariate Statistical Analysis. John Wiley & Sons, 1984.
  24. N. Cressie. Statistic for Spatial Data. John Wiley & Sons, 1993. DOI: https://doi.org/10.1002/9781119115151
  25. P. Diggle, P. Ribeiro. Model-Based Geostatistics. 14th Simposio Nacional de Probabilidade e Estatística, Associacao Brasileira de Estatística, 2000.
  26. P. Diggle, P. Ribeiro. Model-Based Geostatistics. Springer, 2007. DOI: https://doi.org/10.1007/978-0-387-48536-2
  27. E. Lehmann, G. Casella. Theory of Point Estimation. Springer-Verlag, 1998.
  28. I. Cardoso De Oliveira, D. Ferreira. “Multivariate extension of Chi-squared univariate normality test ”. Journal of Statistical Computation and Simulation. vol. 80, no. 5, 513-526, 2010. DOI: https://doi.org/10.1080/00949650902731377
  29. R Core Team. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/. 2019.
  30. P. Ribeiro, P. Diggle. “geoR: A package for geostatistical analysis ”. Journal of Statistical Computation and Simulation. vol. 1, no. 2, 14-18, 2007.
  31. E. Pebesma, R. Bivand. “S classes and methods for spatial data: The sp package ”. R news, vol. 5, no. 2, 9-13, 2005.
  32. J. Gross, U. Ligges. nortest: Tests for Normality. R package version 1.0-4, URL https: //CRAN.Rproject. org/package=nortest. 2015.
  33. Dudewicz E, Mishra S. Modern Mathematical Statistics. John Wiley & Sons, 1988.
  34. H. R. Vega, E. Manzanares, V.M. Hernández, G. A. Mercado, E. Gallego y A. Lorente,
  35. “Características dosimétricas de fuentes isotópicas de neutrones”, Revista Mexicana de Física, vol. 51, no. 5, pp. 494-501, 2005.
  36. H. R. Vega y C. Torres, “Low energy neutrons from a 239PuBe isotopic neutron source inserted in moderating media”, Revista Mexicana de Física, vol. 48, no. 5, pp. 405-412, 2002.
  37. N. C. Tam, J. Bagi y L. Lakosi, “Determining Pu isotopic composition and Pu content of PuBe sources by neutron coincidence technique”, Nuclear Instruments and Methods in Physics Research, vol. 262, pp. 75-80, 2007. DOI: https://doi.org/10.1016/j.nimb.2007.05.005
  38. I. ElAgib, J. Csikai, J. Jordanova y L. OlaAh, “Leakage neutron spectra from spherical samples with a Pu-Be source”, Applied Radiation and Isotopes, vol. 51, pp. 329-333, 1999. DOI: https://doi.org/10.1016/S0969-8043(99)00046-9
  39. J. Bagi, N. C. Tam y L. Lakosi, “Assessment of the Pu content of Pu-Be neutron sources”, Nuclear Instruments and Methods in Physics Research, vol. 222, pp. 242-248, 2004. DOI: https://doi.org/10.1016/j.nimb.2003.12.085
  40. R. H. Zachary, “Neutron flux and energy characterization of a plutonium-beryllium isotopic neutron source by Monte Carlo simulation with verification by neutron activation analysis”. Las Vegas, USA: University of Nevada, 2010.
  41. N. A. Carrillo y H. R. Vega, “Cálculo de los espectros de neutrones de una fuente isotópica moderada”. Presentado en 5as Jornadas de Investigación de la UAZ, CB/UEN-10/042, 2001.
  42. B. Pelowitz, “MCNPX User’s Manual version 2.5.0 Los Alamos National Laboratory Report LA-UR-02-2607”. Presentado en Computation Topical Meeting, Avignon, France, 2005.

Downloads

Download data is not yet available.

Similar Articles

1 2 > >> 

You may also start an advanced similarity search for this article.