Accession Number:

AD1000456

Title:

Bayesian Cubic Spline in Computer Experiments

Descriptive Note:

[Technical Report, Book Chapter]

Corporate Author:

Georgia Tech Research Corporation

Personal Author(s):

Report Date:

2015-07-23

Pagination or Media Count:

30

Abstract:

Cubic splines are commonly used in numerical analysis. It has also become popular in the analysis of computer experiments, thanks to its adoption by the software JMP8.0.2 2010. In this paper a Bayesian version of the cubic spline method is proposed, in which the random function that represents prior uncertainty about y is taken to be aspecific stationary Gaussian process and y is the output of the computer experiment.An MCMC procedure is developed for updating the prior given the observed y values. Simulation examples and a real data application are given to show that the proposed Bayesian method performs better than the frequentist cubic spline method and the standard method based on the Gaussian correlation function.

Descriptors:

Subject Categories:

  • Numerical Mathematics

Distribution Statement:

[A, Approved For Public Release]