Design and analysis of physical and computer experiments

拟议的研究涵盖两个领域。第一个领域是计算机实验的设计和分析。计算机模型被广泛应用于几乎所有的科学和工程领域来模拟物理过程。计算机模型或代码需要一组输入，其中一些是已知的，另一些是未知的。当物理实验成为可能时，可以使用统计模型来组合来自计算机代码的数据和来自物理过程的数据。统计模型可用于估计未知输入、校准问题，并帮助评估计算机模型如何很好地表示真实的物理过程以及与来自模型的预测相关联的不确定性、验证问题。校准的重要应用出现在宇宙学和暗物质结构形成的研究中，在这些领域，最近的观测研究使将物理数据和计算机模型的结果结合起来以提取宇宙学参数的准确估计变得非常重要。在全球气候模型中，评估计算机模型是否能很好地代表现实，并根据模型做出具有相关不确定性界限的预测是非常重要的。其次，考虑了物理过程的实验设计，重点讨论了用于工业产品改进的析因实验设计的有效策略。

Two areas are covered in the proposed research. The first area is the design and analysis of computer experiments. Computer models are widely used in almost every area of science and engineering to model physical processes. The computer model or code requires a set of inputs, some of which are known and others are unknown. When physical experimentation is possible statistical models can be used to combine data from the computer code and data from the physical process. The statistical model can be used to estimate the unknown inputs, the calibration problem, and help assess how well the computer model represents the true physical process and the uncertainty associated with predictions from the model, the validation problem. Important application of calibration arise in cosmology and the study of dark matter structure formations where recent observational studies have made it very important to combine physical data and results from computer models to extract accurate estimates of cosmological parameters. Assessing how well the computer model represents reality and making predictions from the model with associated uncertainty bounds is very important in global climate modeling. Secondly, the design of experiments for physical processes is considered with a focus on efficient strategies for the design of factorial experiments used for industrial product improvement.