...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Educational and Psychological Measurement >A Comparison of Winsteps and Bilog-Mg for Vertical Scaling with the Rasch Model
【24h】

A Comparison of Winsteps and Bilog-Mg for Vertical Scaling with the Rasch Model

机译：Rastep模型将Winsteps和Bilog-Mg用于垂直缩放的比较

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

The present study compares vertical scaling results for the Rasch model from BILOGMG and WINSTEPS. The item and ability parameters for the real and simulated mathematics tests were scaled across five grades, second to sixth. The simulated data were based on real data for a series of mathematics tests for Grades 2 to 6. The results from WINSTEPS and BILOG-MG were compared in terms of differences and correlations between estimated item and ability parameters. Generally, WINSTEPS appeared to capture the individual and mean estimates more accurately, and BILOG-MG captured the standard deviations more accurately. However, because of the many possible variations in vertical scaling studies, the generalizability of these specific findings may be limited. More important, the findings illustrate that choice of software, in addition to data collection and scaling method decisions, influences vertical scaling results.
机译：本研究比较了BILOGMG和WINSTEPS的Rasch模型的垂直缩放结果。真实和模拟数学测试的项目和能力参数分为五个等级，第二至第六级。模拟数据基于2到6年级一系列数学测试的真实数据。比较了WINSTEPS和BILOG-MG的结果，其中包括估计项目和能力参数之间的差异和相关性。通常，WINSTEPS似乎可以更准确地捕获个人和均值估计，而BILOG-MG可以更准确地捕获标准差。但是，由于垂直缩放研究中可能存在许多变化，因此这些特定发现的可概括性可能受到限制。更重要的是，调查结果表明，除了数据收集和缩放方法决策外，软件的选择还会影响垂直缩放结果。

著录项

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