Lawrence Rudner




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. Accessed 2,759 times on https://pareonline.net from July 26, 2016 to December 31, 2019. For downloads from January 1, 2020 forward, please click on the PlumX Metrics link to the right.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.