CBMS Conference: Bayesian Modeling for Spatial and Spatio-Temporal Data

该奖项支持将于2017年8月14日至18日在圣克鲁斯的加州大学举行的CMBS区域会议“空间和时空数据的贝叶斯建模”。主讲人是来自杜克大学的艾伦·盖尔范德。空间和时空数据的层次贝叶斯建模方法是统计科学中一个非常重要的研究领域，具有广泛的应用。然而，空间和时空建模的所有领域的爆炸性增长产生了大量的文献，对于新手来说可能是令人生畏的，对该领域施加了陡峭的进入壁垒。会议讲座将通过提供空间统计的贝叶斯方法的全面回顾来促进对该主题的介绍。既定的研究人员，新人和学生将有机会学习和讨论的主要思想，现代建模和计算方法，以及在该领域的最新成果。会议将加强美国西部多个研究小组之间的联系和合作。该奖项将支持约30名参与者，优先考虑初级研究人员。其他讲座将由Sudipto Banerjee（加州大学洛杉矶分校），Michele Guindani（加州大学欧文分校）和Christopher Querorek（加州大学伯克利分校）提供。所有三位演讲者都在空间数据贝叶斯建模的理论、方法和应用方面具有研究专长，他们的讲座将与主要讲座相辅相成。更多信息请访问会议网页：https://cbms.soe.ucsc.edu

This award supports the CMBS regional conference "Bayesian Modeling for Spatial and Spatio-Temporal Data" to be held at the University of California, Santa Cruz, August 14-18, 2017. The principal speaker is Alan Gelfand from Duke University. Hierarchical Bayesian methods for modeling spatial and spatio-temporal data constitute an extremely important area of research in the statistical sciences, with a wide range of applications. However, the explosive growth in all areas of spatial and spatio-temporal modeling has produced a massive body of literature that can be daunting for newcomers, imposing a steep entry barrier into the field. The conference lectures will facilitate introduction to the subject by providing a comprehensive review of Bayesian methods for spatial statistics. Established researchers, newcomers, and students will have the opportunity to learn and discuss the major ideas, modern modeling and computing methods, and recent results in the field. The conference will strengthen links and collaborations between multiple groups of researchers in the western United States. This award will support about 30 participants, with priority given to junior researchers.Additional lectures will be presented by Sudipto Banerjee (University of California, Los Angeles), Michele Guindani (University of California, Irvine), and Christopher Paciorek (University of California, Berkeley). All three speakers have research expertise in theory, methods, and applications of Bayesian modeling for spatial data, and their lectures will be constructed to be complementary to the main lectures.More information can be found at the conference webpage: https://cbms.soe.ucsc.edu