文章基本信息

标题：Accuracy of Bayes and Logistic Regression Subscale Probabilities for Educational and Certification Tests
本地全文：下载
作者：Lawrence Rudner ; The Arcturus Group
期刊名称：Practical Assessment, Research and Evaluation
印刷版ISSN：1531-7714
电子版ISSN：1531-7714
出版年度：2016
卷号：21
期号：8
出版社：ERIC: Clearinghouse On Assessment and Evaluation
摘要：In the machine learning literature, it is commonly accepted as fact that as calibration sample sizesincrease, Naïve Bayes classifiers initially outperform Logistic Regression classifiers in terms ofclassification accuracy. Applied to subtests from an on-line final examination and from a highlyregarded certification examination, this study shows that the conclusion also applies to theprobabilities estimated from short subtests of mental abilities and that small samples can yieldexcellent accuracy. The calculated Bayes probabilities can be used to provide meaningful examineefeedback regardless of whether the test was originally designed to be unidimensional