Bayesian treed Gaussian process models with an application to computer modeling
Methodology
2009-03-17 v9 Applications
Computation
Abstract
Motivated by a computer experiment for the design of a rocket booster, this paper explores nonstationary modeling methodologies that couple stationary Gaussian processes with treed partitioning. Partitioning is a simple but effective method for dealing with nonstationarity. The methodological developments and statistical computing details which make this approach efficient are described in detail. In addition to providing an analysis of the rocket booster simulator, our approach is demonstrated to be effective in other arenas.
Cite
@article{arxiv.0710.4536,
title = {Bayesian treed Gaussian process models with an application to computer modeling},
author = {Robert B. Gramacy and Herbert K. H. Lee},
journal= {arXiv preprint arXiv:0710.4536},
year = {2009}
}
Comments
32 pages, 9 figures, to appear in the Journal of the American Statistical Association