What is it about?

All computerized exams, e.g. GRE, SAT, GMAT, TOEFL, MCAT, PCAT, PISA, Swedish SAT, etc., use an item bank (pool of high-quality test questions) with known properties of items (e.g. Item difficulty, discrimination and guessing) to quantify the student's ability to answer the question. These are large scale tests and after some period of time some questions (items) become obsolete or exposed out among the students. So, we always need to update item bank with new items with known characteristics. For this, we use item calibration. Calibration is a process to estimate characteristics of new items. This research paper uses the concept of optimal restricted designs and show that this concept naturally fits to item calibration. We can also use this technique in paper-pencil exams.

Featured Image

Read the Original

This page is a summary of: Optimal Item Calibration for Computerized Achievement Tests, Psychometrika, June 2019, Springer Science + Business Media,
DOI: 10.1007/s11336-019-09673-6.
You can read the full text:

Read

Contributors

The following have contributed to this page