• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Using Data Mining to Model Student Achievement on the 4 th Grade TIMSS 2015 Mathematics Assessment: A Five Nation Study
【24h】

Using Data Mining to Model Student Achievement on the 4 th Grade TIMSS 2015 Mathematics Assessment: A Five Nation Study

机译：使用数据挖掘对TIMSS 2015四年级数学评估的学生成绩进行建模：五个国家的研究

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Data mining has been successfully used by financial and retail companies since the mid-1960's to create predictive models and reveal unexpected relationships. However, it remains underutilized as a tool in educational research. Large-scale standardized assessment programs such as the Trends in International Mathematics and Science Study (TIMSS) provide vast amounts of data with the potential for providing new insights in education. Five nations, the Republic of Korea, the United States, Germany, Kuwait, and Kazakhstan were selected based on General Response Style theory to represent a spectrum of cultural backgrounds, from acquiescent to midpoint to individualistic (Hastedt, D. & van de Vijver, F. J. R., 2017). The data mining technique of Random Forest was used to create a series of models to predict student achievement in mathematics using items from the TIMSS 2015 4th Grade background questionnaires for students, teachers, and principals. The final collective model reduced the number of variables from 398 to 23 and was able to predict student achievement. Variables of importance included items relating to language, reading, nutrition, experience of educators and student perception of mathematical ability. Individual rankings for variable importance for each nation indicated acquiescent, and midpoint nations shared more variable importance with nations of similar response style than with the collective model. The variable importance ranking for Kazakhstan, the nation representing the individualistic response style, neither aligned well with other nations nor the collective model. Only two variables, the amount of books in the home and the experience of the principal, were highly ranked by all five nations. The large discrepancies between the nation and collective models indicates the need to address local concerns when forming education policy.
机译：自1960年代中期以来，金融和零售公司已成功使用数据挖掘来创建预测模型并揭示意外关系。但是，它仍然没有被充分利用作为教育研究的工具。诸如国际数学和科学研究趋势（TIMSS）之类的大规模标准化评估计划可提供大量数据，并有可能为教育提供新的见解。根据一般回应风格理论，选择了五个国家，即大韩民国，美国，德国，科威特和哈萨克斯坦，以代表从默认到中点再到个人主义的各种文化背景（Hastedt，D。和van de Vijver， FJR，2017）。随机森林的数据挖掘技术被用来创建一系列模型，使用TIMSS 2015四年级背景调查表中的项目为学生，教师和校长预测学生的数学成绩。最终的集体模型将变量的数量从398个减少到23个，并且能够预测学生的成绩。重要变量包括与语言，阅读，营养，教育者的经验以及学生对数学能力的感知有关的项目。对于每个国家而言，重要性可变的个人排名是默认的，中点国家在响应方式相似的国家中的重要性比在集体模型中的国家大。哈萨克斯坦的可变重要性等级（代表个人主义应对方式的国家）与其他国家或集体模型均未很好地吻合。在所有五个国家中，只有两个变量，即家庭中的书籍数量和校长的经历，被高度排名。国家和集体模式之间的巨大差异表明，在制定教育政策时需要解决当地的担忧。

著录项

  • 作者

    Siemssen, Annette M.;

  • 作者单位

    The University of Texas at El Paso.;

  • 授予单位 The University of Texas at El Paso.;
  • 学科 Mathematics education.;Education.;Statistics.
  • 学位 Ph.D.
  • 年度 2018
  • 页码 256 p.
  • 总页数 256
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 语言学;
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号