Workshop on: Discovery in Complex or Massive Datasets: Common Statistical Themes

点击翻译按钮获取中文摘要

The amount and complexity of data generated to support contemporary science continues to grow rapidly. In domains from genomics to climate science, statisticians are actively engaged in interdisciplinary research teams. The history of statistics shows that, while frequently arising in response to challenges in specific scientific domains such as these, statistical methods and theory often achieve their full range and power from later application to subjects far remote from those of origin. The study of the ``intersections'' -- statistical problems, theories and methods that are relevant to multiple domains of scientific enquiry -- thus offers great opportunity in today's Age of Information.The proposed workshop responds to this opportunity: it aims to enumerate today's most intellectually compelling statistical challenges arising out of these intersections, in the hope of stimulating future research advances that will extend and enhance our data analytic toolkit for scientific discovery. The proceedings and discussions of the workshop will be distilled into a 10-15 page report, which will be disseminated widely by NSF through its website and other usual channels. This workshop and report respond to a number of compelling national needs: a) enhancing the nation's ``methodologic infrastructure'' for research, by advancing the capability of statistical theories and methods to contribute to discovery from massive and/or complex datasets, b) through promotion of research on statistical intersections, to advance the pre- and post- doctoral level training of research statisticians who will be critically needed core faculty members in expanding graduate and undergraduate degree programs in statistics in the U.S., c) fostering the flow of ideas between disciplines, as analysis methods developed in one domain are transferred in other areas.