NotesFAQContact Us
Collection
Advanced
Search Tips
Back to results
Peer reviewed Peer reviewed
Direct linkDirect link
ERIC Number: EJ1108822
Record Type: Journal
Publication Date: 2016-Jul
Pages: 10
Abstractor: As Provided
ISBN: N/A
ISSN: EISSN-1531-7714
Accuracy of Bayes and Logistic Regression Subscale Probabilities for Educational and Certification Tests
Rudner, Lawrence
Practical Assessment, Research & Evaluation, v21 n8 Jul 2016
In the machine learning literature, it is commonly accepted as fact that as calibration sample sizes increase, Naïve Bayes classifiers initially outperform Logistic Regression classifiers in terms of classification accuracy. Applied to subtests from an on-line final examination and from a highly regarded certification examination, this study shows that the conclusion also applies to the probabilities estimated from short subtests of mental abilities and that small samples can yield excellent accuracy. The calculated Bayes probabilities can be used to provide meaningful examinee feedback regardless of whether the test was originally designed to be unidimensional.
Dr. Lawrence M. Rudner. e-mail: editor@pareonline.net; Web site: http://pareonline.net
Publication Type: Journal Articles; Reports - Research
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A