2014 Summer School in Statistics for Astronomers, June 2-13, 2014

2014年十年一度的天文学家统计暑期学校；2014年6月2日至13日；宾夕法尼亚州立大学、大学公园、州立学院、巴黎州立大学非常受欢迎的天体统计暑期学校自2005年开办以来，共培训了575多名参与者。如果保持稳定状态，这项活动将培训约10%的美国年轻天文学家，为美国科学工作者提供关键技能。面向研究生和年轻的研究人员，参与者将接受由高技能教师教授的统计方法论的强烈沉浸。三管齐下的课程提供现代统计学基本原理的指导，接触在天文学中有用的先进方法，以及统计软件的实践培训。与会者带着在统计学及其在科学中的应用方面的更高专业知识，更好地理解如何将这些材料传授给他人，以及对统计在科学中的价值和意义有了很好的欣赏。讲师们花了相当大的精力来调整课程材料以适应他们的受众，课程也在继续发展。基于这一课程的正式教科书于2012年出版。天文学研究通常涉及对天空的成像、光度和光谱测量，产生TB和PetA字节的数据库和10亿个天体的星表。测量科学是不久的将来的天文学，有了新一代令人敬畏的望远镜和各种天文数据集的联邦。虽然希望是巨大的，但实现科学目标关键取决于使用统计推断提取有用的知识，特别是使用先进的统计方法。因此，观测天文学家面临着比以往任何时候都更广泛的统计学挑战，而不幸的是，大多数美国天文学家在统计学方面没有得到很好的培训，他们只通过物理学家撰写的书籍和为他们编写的书籍学习基本方法。这类卷通常只涉及很小范围的问题，在数理统计中提供的概念基础不足，在高级应用统计中几乎没有指导。统计学是一种可利用的技术，必须利用它来推动天文学和天体物理学的需求。2014年青年天文学家统计推断暑期学校将使用经验丰富的教师和创新的课程，在中级水平上介绍概念和方法。这是十年一次的课程，根据过去学员的意见，2014年的课程为期两周，分为三个独立的模块：第一周为天文学家提供的常规统计推理课程，为期两天的“宇宙人口统计建模”补充课程，以及为期三天的“用于天文数据分析和贝叶斯计算的高性能计算”课程。宾夕法尼亚州立大学研究计算和网络基础设施集团及其网络科学研究所正在提供技术人力，并在一定程度上支持高性能计算。

2014 Decennial Summer School in Statistics for Astronomers; June 2-13 2014; Pennsylvania State University, University Park, State College, PAPenn State's very popular astrostatistics summer school has trained over 575 total participants since its inauguration in 2005. If maintained at a steady state, this activity will train about 10% of the nation's young astronomers, providing critical skills to the US scientific workforce. Oriented towards graduate students and young researchers, participants receive an intense immersion in statistical methodology taught by highly skilled instructors. The three-pronged curriculum provides instruction in the underlying principles of modern statistics, exposure to advanced methodologies useful in astronomy, and hands-on training in statistical software. Attendees come away with a much heightened expertise in statistics and its applications to their science, a better understanding of how to teach this material to others, and a fine appreciation for the value and meaning of statistics in science. The instructors have devoted considerable effort to adapting the course material to their audience, and the curriculum continues to evolve. The formal textbook based on this curriculum was published in 2012.Astronomical research often involves imaging, photometric and spectroscopic surveys of the sky that produce tera- and peta-byte databases and billion-object catalogs. Survey science is the astronomy of the near future, with a new generation of formidable telescopes and the federation of diverse astronomical datasets. While the promise is great, achieving the scientific goals depends critically on extraction of useful knowledge using statistical inference, and especially the use of advanced statistical methods. Observational astronomers are thus confronting a wider range of statistical challenges than ever before, while unfortunately most U.S. astronomers are not well trained in statistics, learning only elementary methods through books written by and for physical scientists. Such volumes usually treat only a narrow range of problems, providing inadequate conceptual foundations in mathematical statistics and little guidance in advanced applied statistics. Statistics is an available technology that must be tapped to advance the needs of astronomy and astrophysics.The 2014 Summer School in statistical inference for young astronomers will present concepts and methodologies at an intermediate level, using experienced instructors and an innovative curriculum. This being the decennial offering, and based on comments from the past school participants, the 2014 school covers a two-week extended period of instruction, divided into three independent modules: the regular statistical inference course for astronomers in the first week, a two-day supplement on 'Statistical modeling of cosmic populations', and a three-day school on 'High-Performance Computing for Astronomical Data Analysis & Bayesian Computing'. The Penn State Research Computing & Cyberinfrastructure Group, and its Institute for CyberScience, are providing technical manpower and partially supporting the high-performance computing.