International Postdoctoral Fellows: Optimal Design for Nonlinear Regression

国际博士后研究员：非线性回归的优化设计

• 批准号: 9403367
• 负责人: Timothy O'Brien
• 金额: $ 1.85万
• 依托单位: Washington State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1994
• 资助国家: 美国
• 起止时间: 1994-09-01 至 1996-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9403367&HistoricalAwards=false
• 关键词: International; Postdoctoral; Fellows; Optimal; Design

9403367 O'Brien This award is under the International Junior Investigator and Postdoctoral Fellows Program, which enables U.S. scientists and engineers to conduct three to twelve months of research abroad at research centers of proven excellence. The program's awards provide opportunities for joint research, and the use of unique or complementary facilities, expertise and experimental conditions abroad. This award will support a seven-month postdoctoral research visit by Dr. Timothy E. O'Brien of Washington State University to work with Professor Dr. Friedrich Pukelsheim at the Institut fur Mathematik der Universitat Augsburg on optimal design for nonlinear regression models. This research will focus on several specific problems. First, development of a theoretical framework will help researchers select among design procedures available for nonlinear models. Second, extension of existing second- order and Bayesian design procedures to accommodate the multi-response and/or compartmental nonlinear models that face many researchers. Third, elevation of compound design procedures for nonlinear models so that researchers can obtain optimal designs even when they are unsure which model they should use. In addition to enhancing the theoretical understanding of statistics, the results of this work will furnish scientists in other fields with efficient tools to accomplish their research. ***

9403367 O'Brien该奖项是国际青年研究员和博士后研究员计划的一部分，该计划使美国科学家和工程师能够在国外公认的卓越研究中心进行三到十二个月的研究。该计划的奖励为联合研究提供了机会，并利用独特或互补的设施、专业知识和国外的实验条件。该奖项将支持华盛顿州立大学的Timothy E. O'Brien博士进行为期七个月的博士后研究访问，与奥格斯堡大学数学研究所的Friedrich Pukelsheim教授一起研究非线性回归模型的最佳设计。本研究将集中于几个具体问题。首先，理论框架的发展将有助于研究人员在可用于非线性模型的设计过程中进行选择。其次，扩展现有的二阶和贝叶斯设计程序，以适应许多研究人员面临的多响应和/或分区非线性模型。第三，提高非线性模型的复合设计程序，使研究人员即使在不确定应该使用哪种模型的情况下也能获得最佳设计。除了加强对统计学的理论认识外，这项工作的结果将为其他领域的科学家提供完成研究的有效工具。＊＊＊