Prediction of non-stationary response functions using a Bayesian composite Gaussian process

DOI10.1016/j.csda.2020.107083OpenAlexW3082988878MaRDI QIDQ829711

Christopher M. Hans, Casey B. Davis, Thomas J. Santner

Publication date: 6 May 2021

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.csda.2020.107083

zbMATH Keywords

emulatoruncertainty quantificationuniversal krigingcomposite Gaussian process modelGaussian process interpolatortreed Gaussian process model

Mathematics Subject Classification ID

Statistics (62-XX)

Related Items

Statistical test for anomalous diffusion based on empirical anomaly measure for Gaussian processes

Uses Software

• tgp
• Virtual library
• CGP

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Cases for the nugget in modeling computer experiments
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Optimal scaling for various Metropolis-Hastings algorithms.
• Design and analysis of computer experiments. With comments and a rejoinder by the authors
• The design and analysis of computer experiments
• Composite Gaussian process models for emulating expensive functions
• Robust Gaussian stochastic process emulation
• Bayesian Treed Gaussian Process Models With an Application to Computer Modeling
• Stochastic Kriging for Simulation Metamodeling
• Warped Gaussian Processes and Derivative-Based Sequential Designs for Functions with Heterogeneous Variations
• A non-stationary covariance-based Kriging method for metamodelling in engineering design
• Strictly Proper Scoring Rules, Prediction, and Estimation