Orthonormal residuals in geostatistics: Model criticism and parameter estimation

In linear geostatistics, models for the mean function (drift) and the variogram or generalized covariance function are selected on the basis of the modeler's understanding of the phenomenon studied as well as data. One can seldom be assured that the most appropriate model has been selected; however, analysis of residuals is helpful in diagnosing whether some important characteristic of the data has been neglected and, ultimately, in providing a reasonable degree of assurance that the selected model is consistent with the available information. The orthonormal residuals presented in this work are kriging errors constructed so that, when the correct model is used, they are uncorrelated and have zero mean and unit variance. It is suggested that testing of orthonormal residuals is a practical way for evaluating the agreement of the model with the data and for diagnosing model deficiencies. Their advantages over the usually employed standardized residuals are discussed. A set of tests are presented. Orthonormal residuals can also be useful in the estimation of the covariance (or variogram) parameters for a model that is considered correct.

[1]  B. Anderson,et al.  Optimal Filtering , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[2]  Peter K. Kitanidis,et al.  Statistical estimation of polynomial generalized covariance functions and hydrologic applications , 1983 .

[3]  Beat Kleiner,et al.  Graphical Methods for Data Analysis , 1983 .

[4]  George E. P. Box,et al.  Sampling and Bayes' inference in scientific modelling and robustness , 1980 .

[5]  Leon E. Borgman,et al.  A note on the asymptotic distribution of the sample variogram , 1982 .

[6]  D. F. Andrews,et al.  Significance tests based on residuals , 1971 .

[7]  S. Shapiro,et al.  An Analysis of Variance Test for Normality (Complete Samples) , 1965 .

[8]  B. M. Davis.  Uses and abuses of cross-validation in geostatistics , 1987 .

[9]  F. J. Anscombe,et al.  The Examination and Analysis of Residuals , 1963 .

[10]  John M. Chambers,et al.  Graphical Methods for Data Analysis , 1983 .

[11]  P. Kitanidis,et al.  Maximum likelihood parameter estimation of hydrologic spatial processes by the Gauss-Newton method , 1985 .

[12]  K. Mardia.  Minimum norm quadratic estimation of components of spatial covariance , 1985 .

[13]  Donald E. Myers.  On variogram estimation , 1991 .

[14]  J. Filliben.  The Probability Plot Correlation Coefficient Test for Normality , 1975 .

[15]  Leon E. Borgman,et al.  New advances in methodology for statistical tests useful in geostatistical studies , 1988 .

[16]  S. P. Neuman,et al.  estimation of spatial covariance structures by adjoint state maximum likelihood cross validation: 1. Theory , 1989 .

[17]  Olivier Dubrule,et al.  Cross validation of kriging in a unique neighborhood , 1983 .

[18]  P. Delfiner,et al.  Linear Estimation of non Stationary Spatial Phenomena , 1976 .

[19]  Peter K. Kitanidis,et al.  Analysis of the Spatial Structure of Properties of Selected Aquifers , 1985 .

[20]  Andre G. Journel,et al.  Geostatistics: Models and tools for the earth sciences , 1986 .

[21]  E. G. Vomvoris,et al.  A geostatistical approach to the inverse problem in groundwater modeling (steady state) and one‐dimensional simulations , 1983 .

[22]  G. C. Tiao,et al.  Bayesian inference in statistical analysis , 1973 .

[23]  N. Cressie.  Fitting variogram models by weighted least squares , 1985 .

[24]  Peter K. Kitanidis,et al.  PARAMETRIC ESTIMATION OF COVARIANCES OF REGIONALIZED VARIABLES , 1987 .

[25]  E. T. Jaynes,et al.  Where do we Stand on Maximum Entropy , 1979 .