arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1809.05731stat.OT
收藏

Inter-Rater:通过排列多个用户对来分析评分员间可靠性的软件

Inter-Rater: Software for analysis of inter-rater reliability by permutating pairs of multiple users

Daniel J. Arenas

摘要:

互评者量化了评价一组受试者的多名评分者之间的可靠性。它计算群体数量,Fleiss kappa,并通过保存每个用户的信息和量化每个用户与群体其他成员的一致性来改进现有软件。这是通过用户对的排列来实现的。该软件是用Python编写的,可以在Linux上运行,代码存放在Zenodo和GitHub上。该软件可用于系统评价、医学诊断算法、教育应用等方面的评价者间可靠性评价。

英文摘要:

Inter-Rater quantifies the reliability between multiple raters who evaluate a group of subjects. It calculates the group quantity, Fleiss kappa, and it improves on existing software by keeping information about each user and quantifying how each user agreed with the rest of the group. This is accomplished through permutations of user pairs. The software was written in Python, can be run in Linux, and the code is deposited in Zenodo and GitHub. This software can be used for evaluation of inter-rater reliability in systematic reviews, medical diagnosis algorithms, education applications, and others.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑