Abstract
Isotropic covariance functions are successfully used to model spatial continuity in a multitude of scientific disciplines. Nevertheless, a satisfactory characterization of the class of permissible isotropic covariance models has been missing. The intention of this note is to review, complete, and extend the existing literature on the problem. As it turns out, a famous conjecture of Schoenberg (1938) holds true: any measurable, isotropic covariance function on ℝd (d ≥ 2) admits a decomposition as the sum of a pure nugget effect and a continuous covariance function. Moreover, any measurable, isotropic covariance function defined on a ball in ℝd can be extended to an isotropic covariance function defined on the entire space ℝd.
Similar content being viewed by others
REFERENCES
Armstrong, M., and Diamond, P., 1984, Testing variograms for positive-definiteness: Math. Geology, v. 16, no. 4, p. 407–421.
Cambanis, S., Huang, S., and Simons, G., 1981, On the theory of elliptically contoured distributions: Jour. Multivariate Analysis, v. 11, no. 3, p. 368–385.
Christakos, G., 1984. On the problem of permissible covariance and variogram models: Water Resources Res., v. 20, no. 2, p. 251–265.
Christakos, G., 1992, Random field models in earth sciences: Academic Press, San Diego, 474 p.
Cressie, N. A. C., 1993, Statistics for spatial data, 2nd Ed.: John Wiley, New York, 900 p.
Crum, M. M., 1956, On positive-definite functions: Proc. London Math. Soc., Third Ser., v. 6, no. 24, p. 548–560.
Dickinson, B. W., 1980, Two-dimensional Markov spectrum estimates need not exist: IEEE Trans. Inform. The., v. IT-26, no. 1, p. 120–121.
Gneiting, T., 1998a, Decomposition theorems for αa-symmetric positive definite functions: Math. Nachr., in press.
Gneiting, T., 1998b, Isotropic correlation functions on d-dimensional balls: Adv. Appl. Probab., in press.
Guttorp, P., 1994, Comment: Jour. Am. Statis. Assoc., v. 89, no. 426, p. 382–384.
Matérn, B., 1986, Spatial variation, 2nd Ed., Lecture notes in statistics, v. 36: Springer, Berlin, 151 p.
Ripley, B. D., 1981, Spatial statistics: Wiley, New York, 252 p.
Rudin, W., 1963, The extension problem for positive-definite functions: Illinois Jour. Math., v. 7, no. 3, p. 532–539.
Rudin, W., 1970, An extension theorem for positive-definite functions: Duke Math. Jour., v. 37, no. 1, p. 49–53.
Sampson, P. D., and Guttorp, P., 1992, Nonparametric estimation of nonstationary spatial covariance structure: Jour. Am. Statis. Assoc., v. 87, no. 417, p. 108–119.
Sasvári, Z., 1986, The extension problem for measurable positive definite functions: Math. Zeitschr., v. 191, no. 3, p. 475–478.
Sasvári, Z., 1987, Decomposition of positive definite functions defined on a neighbourhood of the identity: Monatsh. Math., v. 104, no. 2, p. 139–148.
Sasvári, Z., 1994, Positive definite and definitizable functions: Akademie Verlag, Berlin, 208 p.
Schoenberg, I. J., 1938, Metric spaces and completely monotone functions: Ann. of Math., v. 39, no. 4, p. 811–841.
Tewfik, A. H., Levy, B. C., and Willsky, A. S., 1988, An efficient maximum entropy technique for 2-d isotropic random fields: IEEE Trans. Acoust. Speech Signal Processing, v. 36, no. 5, p. 797–812.
Zimmerman, D. L., 1993, Another look at anisotropy in geostatistics: Math. Geology, v. 25, no. 4, p. 453–470.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Gneiting, T., Sasvári, Z. The Characterization Problem for Isotropic Covariance Functions. Mathematical Geology 31, 105–111 (1999). https://doi.org/10.1023/A:1007597415185
Issue Date:
DOI: https://doi.org/10.1023/A:1007597415185