STATISTICS USING MIDAS: DATA ANALYSIS OVER THE INTERNET

SBIR项目将全面开发和实施一个多变量动态数据分析系统（MIDAS），通过互联网提供广泛的交互式数据分析访问，包括145个主要的健康和社会科学数据库，其中包含来自七个Sociometrics国家数据实现的150,000多个变量（http://www.socio.com）。MIDAS将包括搜索和检索程序，以及高度组织的变量级和研究级链接，链接到数千页的支持文档，例如原始仪器、代码本、用户指南和方法报告。集成的javascript接口将允许用户通过支持java的Internet浏览器快速、轻松、廉价地与系统进行交互。在线数据分析程序将包括加权和非加权频率、百分位数、分散和集中趋势的度量，以及带有关联度量、均值比较（2组和方差分析）和相关性的双向和n向表，以及复方差估计的计算。用户将能够定义用于分析的聚合的案例子集、编码，并生成可下载或打印的输出。也可以下载自定义数据集。MIDAS将包括一个快速统计引擎、最先进的界面和“便携式文档格式”文件，以确保数据分析速度和全面可用性。MIDAS将集成许多Socionet功能，例如，Verity搜索和安全商业交易。Beta测试面板将用于评估和改进所有功能。建议的商业应用：多元交互式数据分析系统的商业可行性基于以下证据：目前对社会计量学数据和仪器档案产品的需求；[2]对在线数据分析的兴趣增加，[3]当前的竞争水平较低，[4]机构目标市场的规模扩大，例如面向卫生和社会科学的学术部门、图书馆和研究组织，这些机构共有几十万名研究人员、教师、学生、参考工作人员和其他对易于使用、可定制的国家卫生和社会科学统计资源在线查询感兴趣的人员。

The SBIR project will fully develop and implement a Multivariate Intractive Data Analysis System (MIDAS) to provide broad access to interactive data analysis, via the Internet, of 145 premier health and social science database containing over 150,000 variables from seven of Sociometrics' national data achieve (http://www.socio.com). MIDAS will include search and retrieval programming and highly organized variable-level and study-level links to several thousand pages of supporting documentation, e.g., original instruments, codebooks, User's Guides, and methodology reports. An integrated javascript interface will allow users to quickly, easily, and inexpensively interact with the system through Java-enabled Internet browsers. Online data analytic procedures will include weighted and unweighted frequencies, percentiles, and measures of dispersion and central tendency, as well as two-way and n-way tables with measures of association, comparison of means (2-group and ANOVA) and correlations, and the calculation of complex variance estimations. Users will be able to define case subsets, recodes, of aggregations for analysis, and them produce output which can be downloaded or printed. Custom dataset download will also be available. MIDAS will include a fast statistical engine, state-of-the-art interface, and "portable document format" files to ensure data analytic speed and comprehensive usability. MIDAS will be integrated with many Socionet features, e.g., Verity search and secure commercial transactions. Beta test panels will be used to assess and improve all features. PROPOSED COMMERCIAL APPLICATION: The commercial viability of the Multivariate Interactive Data Analysis System is based on evidence of: [1] current demand for Sociometrics' data and instrument archive products; [2] increased interest in online data analysis, [3] low levels of current competition, and [4] the size of institutional target markets, such as health and social science-oriented academic departments, libraries, and research organizations, which total several hundred thousand researchers, teachers, students, reference staff, and others interested in easy-to-use, customizable, online queries of national health and social science statistical resources.