Probability Theory and Related Fields

, Volume 99, Issue 3, pp 399–424 | Cite as

Properties of nonparametric estimators of autocovariance for stationary random fields

  • Peter Hall
  • Prakash Patil
Article

Summary

We introduce nonparametric estimators of the autocovariance of a stationary random field. One of our estimators has the property that it is itself an autocovatiance. This feature enables the estimator to be used as the basis of simulation studies such as those which are necessary when constructing bootstrap confidence intervals for unknown parameters. Unlike estimators proposed recently by other authors, our own do not require assumptions such as isotropy or monotonicity. Indeed, like nonparametric function estimators considered more widely in the context of curve estimation, our approach demands only smoothness and tail conditions on the underlying curve or surface (here, the autocovariance), and moment and mixing conditions on the random field. We show that by imposing the condition that the estimator be a covariance function we actually reduce the numerical value of integrated squared error.

Mathematics Subject Classification (1991)

62G05 62G20 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Armstrong, A.G., Diamond, P.: Testing variograms for positive-definiteness. Math. Geol.16, 407–421 (1984)Google Scholar
  2. Cheng, K.F., Lin, P.E.: Nonparametric estimation of a regression function. Z. Wahrscheinlichkeitstheor. Verw. Geb.57, 223–233 (1981)Google Scholar
  3. Christakos, G.: On the problem of permissible covariance and variogram models. Water Resources Res.20, 251–265 (1984)Google Scholar
  4. Cressic, N.: Statistics for Spatial Data. New York: Wiley, 1991Google Scholar
  5. Devroye, L., Györfi, L.: Nonparametric Density Estimation: TheL 1 View. New York: Wiley, 1985Google Scholar
  6. Gasser, Th., Müller, H.G.: Kernel estimation of regression functions (Lect. Notes Math., vol. 757, pp. 23–68) Berlin Heidelberg New York: Springer, 1979Google Scholar
  7. Gasser, Th., Müller, H.G.: Estimating regression functions and their derivatives by the kernel method. Scand. J. Stat.11, 171–185 (1984)Google Scholar
  8. Hall, P., Heyde, C.C.: Martingale Limit Theory and its Application. New York: Academic Press, 1980Google Scholar
  9. Hall, P., Fisher, N.I., Hoffmann, B.: On the nonparametric estimation of covariance functions. Research Report, ANU, 1992Google Scholar
  10. Härdle, W.: Applied Nonparametric Regression. Cambridge: University Press, 1990Google Scholar
  11. Härdle, W., Marron, J.S.: Random approximations to some measures of accuracy in nonparametric curve estimation. J. Multivariate Anal.20, 91–113 (1986)Google Scholar
  12. Ibragimov, I.A., Rozanov, Yu.A.: Gaussian Random Processes. Berlin Heidelberg New York: Springer, 1978Google Scholar
  13. Ivanov, A.V., Leonenko, N.N.: Statistical Analysis of Random Fields. Dordrecht: Kluwer, 1989Google Scholar
  14. Journel, A.G., Huijbregts, Ch.J.: Mining Geostatistics. London: Academic Press, 1978Google Scholar
  15. Kovalchuk, T.V.: On convergence of the distribution of functionals of the correlogram of a homogenous random field with unknown mean. Theor. Probab. Math. Stat.35, 45–53 (1987)Google Scholar
  16. Matheron, G.: The Theory of Regionalised Variables. Les Cahiers du Centre de Morphologie Mathematique de Fontainebleau. 5 (1971)Google Scholar
  17. Sampson, P.D., Guttorp, P.: Nonparametric representation of nonstationary spatial covariance structure. J. Am. Stat. Assoc.87, 108–119 (1992)Google Scholar
  18. Schoenberg, I.J.: Metric spaces and completely monotone functions. Ann. Math.79, 811–841 (1938)Google Scholar
  19. Shapiro, A., Botha, J.D.: Variogram fitting with a general class of conditionally nonnegative definite functions. Comput. Stat. Data Anal.11, 87–96 (1991)Google Scholar
  20. Silverman, B.W.: Density Estimation for Statistics and Data Analysis. London: Chapman and Hall, 1986Google Scholar

Copyright information

© Springer-Verlag 1994

Authors and Affiliations

  • Peter Hall
    • 1
  • Prakash Patil
    • 1
  1. 1.Centre for Mathematics and its ApplicationsAustralian National UniversityCanberraAustralia
  2. 2.CSIRO Division of Mathematics and StatisticsLindfieldAustralia

Personalised recommendations