Bootstrapped models for intrinsic random functions
The use of intrinsic random function stochastic models as a basis for estimation in geostatistical work requires the identification of the generalized covariance function of the underlying process, and the fact that this function has to be estimated from the data introduces an additional source of error into predictions based on the model. This paper develops the sample reuse procedure called the ''bootstrap'' in the context of intrinsic random functions to obtain realistic estimates of these errors. Simulation results support the conclusion that bootstrap distributions of functionals of the process, as well as of their ''kriging variance,'' provide a reasonable picture of the variability introduced by imperfect estimation of the generalized covariance function.
- Research Organization:
- Los Alamos National Lab., NM (USA)
- DOE Contract Number:
- W-7405-ENG-36
- OSTI ID:
- 6340930
- Report Number(s):
- LA-UR-87-1150; CONF-8704137-1; ON: DE87008987
- Country of Publication:
- United States
- Language:
- English
Similar Records
Bootstrapped models for intrinsic random functions
Bootstrap procedures for linear, robust, and nonlinear regression: application to pharmacokinetics
Random vectors and spatial analysis by geostatistics for geotechnical applications
Conference
·
Mon Aug 01 00:00:00 EDT 1988
· J. Int. Assoc. Math. Geol.; (United States)
·
OSTI ID:6288095
Bootstrap procedures for linear, robust, and nonlinear regression: application to pharmacokinetics
Thesis/Dissertation
·
Tue Dec 31 23:00:00 EST 1985
·
OSTI ID:7106648
Random vectors and spatial analysis by geostatistics for geotechnical applications
Journal Article
·
Sat Aug 01 00:00:00 EDT 1987
· Math. Geol.; (United States)
·
OSTI ID:5377870