Mathematical Sciences: Bayesian Analysis, Chaos, Stochastic Optimization, and File-Merging Methodology

本课题的研究问题主要集中在四个方面：随机优化问题、贝叶斯分析中的信息论问题、混沌模型中的统计分析问题和微观数据文件的合并问题。随机优化项目预计将开发一种基本上自动化的、可能快速收敛的算法，用于寻找复杂函数的全局最小值。贝叶斯分析领域的信息论研究致力于应用各种信息度量来发展新的理论，以便在两个实验中选择较好的一个。混沌与统计学的研究属于混沌非线性时间序列的贝叶斯统计分析。文件合并方法的统计理论的发展是过去由国家科学基金会支持的一个项目的延续，联邦机构在评估政策影响时大量使用这种方法。

The research problems in this project belong mainly to four areas: Stochastic Optimization, Information Theory in Bayesian Analysis, Statistical Analysis in Chaotic Models, and Problems in Merging Micro-data Files. The stochastic optimization project is expected to develop a mostly automated and possibly fast converging algorithm for finding the global minimum of a complicated function. The investigations in information theory in the Bayesian analysis area are devoted to the application of various information measures to the development of new theories for choosing the better of the two experiments. Investigations under Chaos and Statistics pertain to Bayesian statistical analysis of chaotic nonlinear times series. The development of statistical theory for file-merging methodology, which is used heavily in evaluating policy implications by federal agencies, is a continuation of a project supported by NSF in the past.