CSUMS: NC State University Computation for Undergraduates in Statistics Program (NCSU CUSP)

这个csum项目，NCSU CUSP，准备学生从事一个重要的研究经验，并在计算，数学和统计语言流利。研究者和他的同事们提供探究式学习，以训练本科生用令人兴奋的新方法来解决涉及大量数据集或计算密集型方法的问题。该计划将现代统计分析计算的广泛课程与实践和研究实验室相结合，重点关注药物发现，模式识别，统计遗传学，数据同化或金融风险等应用领域。实习和实验室提供科学背景，统计和计算方法的概述，团队合作和沟通技巧的培训和反馈，以及重要的指导研究经验。在数据挖掘、地球物理和环境数据同化、统计遗传学和生物信息学、贝叶斯分层建模、金融风险建模和时间序列分析等领域进行研究的跨学科团队的教师担任NCSU CUSP的导师，并作为邻近梅雷迪思学院学生的联合导师。NCSU CUSP有四个具体目标。它(1)准备学生利用先进的计算技术，使复杂的计算成为统计和数学方法课程和研究经验的一个组成部分；(2)提高学生的非技术技能，包括公开演讲和书面沟通，团队合作和道德推理；(3)提供研究经验，应用主动性和创造性，开发统计和计算方法来解决跨学科的科学问题；(4)培养和激励多样化的高素质学生从事数学和计算科学领域的跨学科研究生学习。在科技飞速发展的帮助下，许多科学领域每天都会产生大量的新数据，而且数据量正以人类历史上前所未有的速度增长。为了保持美国的竞争力和创新能力，迫切需要一批受过新颖和强大技术培训的多样化研究人员来说明、建模和分析这些大规模、高维和非线性结构化数据。NCSU CUSP以全国最大的统计部门之一的资源为基础，成为全国首批计算密集型本科统计项目之一。该项目将导致新的计算密集型课程和跨学科课程的发展，这将产生长期影响。该项目在一开始就致力于增加计算统计这一新兴领域的多样性。NCSU CUSP提高了数学专业和教师对统计科学的认识，促进了跨学科项目之间的更大合作，并鼓励各种准备良好的学生攻读定量科学的研究生学习。沟通技巧的培训有助于培养能够将科学研究成果带给公众和决策者的毕业生。NCSU CUSP的方法和结果通过区域和国家会议、参加研讨会、CUSP网站和发表文章广泛宣传到数学科学和计算界。该项目得到了MPS数学科学部、MPS多学科活动办公室和本科教育EHR部门的支持。

Ghosh0703392 This CSUMS project, NCSU CUSP, prepares students to engagein a significant research experience, and to be fluent in thelanguages of computing, mathematics, and statistics. Theinvestigator and his colleagues provide inquiry-guided learningto train undergraduates in exciting new approaches to problemsinvolving massive datasets or computationally intensive methods. The program couples extensive coursework in computing forcontemporary statistical analysis with a practicum and researchlab focusing on an area of application such as drug discovery,pattern recognition, statistical genetics, data assimilation, orfinancial risk. The practicum and lab provide scientificbackground, an overview of statistical and computationalapproaches, training and feedback on teamwork and communicationskills, and a significant mentored research experience. Facultymembers from interdisciplinary teams conducting research in theareas of data mining, geophysical and environmental dataassimilation, statistical genetics and bioinformatics, Bayesianhierarchical modeling, financial risk modeling and time seriesanalysis serve as NCSU CUSP mentors and as co-mentors forstudents from neighboring Meredith College. The NCSU CUSP meetsfour specific objectives. It (1) prepares students to takeadvantage of computing advances and make sophisticated computingan integral part of the statistical and mathematical methodologycurriculum and research experience; (2) improves students'non-technical skills, including public speaking and writtencommunication, working in teams, and ethical reasoning, (3)provides the research experience to apply initiative andcreativity in developing statistical and computing approaches tointerdisciplinary scientific problems; and (4) prepares andmotivates a diverse pool of highly qualified students to pursueinterdisciplinary graduate studies in the mathematical andcomputational sciences. Aided by rapid advances in technology, massive amounts ofnew data are generated daily in many scientific disciplines andthe volumes are growing at a rate unprecedented in human history. For the US to remain competitive and innovative, a diverse poolof researchers trained in novel and powerful techniques iscritically needed to illustrate, model, and analyze theselarge-sized, high-dimensional, and nonlinearly-structured data. Building on resources of one of the country's largest statisticsdepartments, NCSU CUSP becomes one of the first computationallyintensive statistics programs for undergraduates in the nation. This project leads to development of new computationallyintensive courses and interdisciplinary courses, which will havea long term impact. The project is also committed at the outsetto increasing diversity in the emerging field of computationalstatistics. NCSU CUSP increases awareness of statistical scienceamong mathematics majors and faculty, fosters greatercollaboration between interdisciplinary programs, and encouragesa diverse pool of well-prepared students to pursue graduatestudies in quantitative sciences. Training in communicationskills helps develop graduates who can bring scientific researchresults to the public and policy makers. NCSU CUSP methods andresults are widely publicized to the mathematical science andcomputational communities through regional and nationalconferences, participation in workshops, a CUSP website, andpublished articles. The project is supported by the MPS Divisionof Mathematical Sciences, the MPS Office of MultidisciplinaryActivities, and the EHR Division of Undergraduate Education.