Single nugget kriging

DOI10.5705/SS.202016.0255MaRDI QIDQ4639567zbMATH OpenOpenAlexFDO

Authors Minyong R. Lee, Art B. Owen

Publication date 9 May 2018

Published in STATISTICA SINICA (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1507.05128

zbMATH Keywords

computer experimentsconditional biasGaussian process regressionpredictions at extreme values

Mathematics Subject Classification ID

Gaussian processes (60G15) Prediction theory (aspects of stochastic processes) (60G25) Design of statistical experiments (62K99) Inference from spatial processes (62M30)

Abstract: We propose a method with better predictions at extreme values than the standard method of Kriging. We construct our predictor in two ways: by penalizing the mean squared error through conditional bias and by penalizing the conditional likelihood at the target function value. Our prediction exhibits robustness to the model mismatch in the covariance parameters, a desirable feature for computer simulations with a restricted number of data points. Applications on several functions show that our predictor is robust to the non-Gaussianity of the function.

Recommendations

• On Prediction Properties of Kriging: Uniform Error Bounds and Robustness
• scientific article; zbMATH DE number 1215451
• Spatial prediction and ordinary kriging
• A comparison of Kriging with nonparametric regression methods
• Kriging by local polynomials.

Cited in

(5)

• Practical Heteroscedastic Gaussian Process Modeling for Large Simulation Experiments
• On the inference of applying Gaussian process modeling to a deterministic function
• Learning with partition of unity-based kriging estimators
• Identifying Nonlinear Dynamics with High Confidence from Sparse Data
• Traffic prediction by combining macroscopic models and Gaussian processes

This page was built for publication: Single nugget kriging

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4639567)