文章基本信息

标题：Goodman–Kruskal Gamma and Dimension-Corrected Gamma in Educational Measurement Settings
本地全文：下载
作者：Jari Metsämuuronen
期刊名称：International Journal of Educational Methodology
电子版ISSN：2469-9632
出版年度：2021
卷号：7
期号：1
页码：95-118
DOI：10.12973/ijem.7.1.95
出版社：Tayfun Yagar
摘要：Although Goodman–Kruskal gamma (G) is used relatively rarely it has promising potential as a coefficient of association in educational settings. Characteristics of G are studied in three sub-studies related to educational measurement settings. G appears to be unexpectedly appealing as an estimator of association between an item and a score because it strictly indicates the probability to get a correct answer in the test item given the score, and it accurately produces perfect latent association irrespective of distributions, degrees of freedom, number of tied pairs and tied values in the variables, or the difficulty levels in the items. However, it underestimates the association in an obvious manner when the number of categories in the item is more than four. Towards this, a dimension-corrected G (G2) is proposed and its characteristics are studied. Both G and G2 appear to be promising alternatives in measurement modelling settings, G with binary items and G2 with binary, polytomous and mixed datasets.
关键词：Item analysis; Goodman–Kruskal gamma; Somers D; Jonckheere–Terpstra test; Pearson correlation.