|
Abstract:
|
Deterministic simulators (``simulators'') based on micro-level mathematical descriptions of the physics or biology of a system are in the forefront of innovations for studying many engineering, biomechanics, and biological systems. This course will provide statistical tools to design and analyze experiments utilizing simulators so as to identify the important factors controlling a given system, to determine the manner in which the factors affect the system, and to optimize the system. The course describes methods for experiments using data from either a simulator-only study or combined data from a physical system and a simulator of the system. The course contains four sections. The first three sections provide tools to design and analyze simulator-only studies; the last uses the material of the first three sections to perform Bayesian calibration analysis using physical/simulator data. The first section provides methods for prediction based on given training data. The second section shows how to design computer experiments. The third section describes methods for conducting ``sensitivity analyses" to identify the influential inputs to a simulator. The final section provides tools to conduct a Bayesian calibration analysis. This course is based on the Second Edition of the book ``The Design and Analysis of Computer Experiments" by Santner, Williams, and Notz (Springer Verlag).
|
