Gaussian Spatial Process with Credible Intervals
The rapid growth in computing power has made the computational simulation of complex systems feasible and helped avoid physical experimentation that might otherwise be too time consuming, costly, or even impossible to observe. The first computer experiment appears to have been conducted by a research team headed by Enrico Fermi at Los Alamos National Labs in 1953. Since then, scientists in diverse areas such as weather modeling, particle physics, aircraft design and chemistry have turned to computer model simulation of complex systems as a way to learn about their respective processes.

With a simulator in hand, scientists are able to adjust inputs to computer codes and observe the impact on a system. Many computer models require the specification of a large number of input settings and/or are computationally demanding. As a result, only a relatively small number of simulation runs tend to be carried out. Scientists must therefore select the simulation trials judiciously and perform a computer experiment. Unlike physical experiments, computer experiments frequently are deterministic - noiseless - and, therefore require new statistical development.

The Program for the Design and Analysis of Computer Experiments for Complex Systems aims to develop new statistical methodology for helping scientists explore complex computer simulators. The types of data structures dealt with are as varied as the applications. One is faced with univariate, multivariate, functional and space-time data, just to name a few. In addition, we are also often faced with large volumes of data. Current collaborations include work with atmospheric scientists, cosmologists and materials scientists. Our goal is to provide efficient and practical methodology for conducting and analyzing computer experiments.