A comparison of different methods for building Bayesian kriging models

Abstract

Kriging is a statistical approach for analyzing computer experiments. Kriging models can be used as fast running surrogate models for computationally expensive computer codes. Kriging models can be built using different methods, the maximum likelihood estimation method and the leave-one-out cross validation method. The objective of this paper is to evaluate and compare these different methods for building kriging models. These evaluation and comparison are achieved via some measures that test the assumptions that are used in building kriging models. We apply kriging models that are built based on the two different methods on a real high dimensional example of a computer code. We demonstrate our evaluation and comparison through some measures on this real computer code.