This section of the appendix covers instructions for computing the following classical item analysis statistics: item difficulty, item discrimination, and distractor analysis. Directions are provided for both dichotomously scored items, such as one would have on a multiple-choice test, as well as for non-dichotomously scored items, such as one would see on a performance assessment. Correlation methods of item discrimination and distractor analysis are covered, as well as the traditional upper-lower method.
Item difficulty, denoted by p, and referred to as the p-value, is the proportion of examinees ...
Get Test Development: Fundamentals for Certification and Evaluation now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
