Graduate Management Admission Council, Reston, VA, USA
© 2018, Korea Health Personnel Licensing Examination Institute
This is an open-access article distributed under the terms of the Creative Commons Attribution License <http://creativecommons.org/licenses/by/4.0/>, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Authors’ contributions
All work was done by Kyung (Chris) Tyek Han.
Conflict of interest
No potential conflict of interest relevant to this article was reported.
Funding
None.
Simulees | 10,000 Simulees with θ–N (0, 1) |
---|---|
Item pool | 300 Items based on a 2-parameter logistic item response theory model |
• ma–U (0.5, 1.2) | |
• b–U (-3, 3) | |
Item selection criterion | Maximum Fisher information |
Item exposure control | Randomesque (randomly select an item from among the 5 best items) |
Test length | Variable length |
• aTerminate when standard error of estimation becomes smaller than 0.3 | |
• bMaximum of 50 items | |
Content balancing | None |
Score estimation | maximum likelihood estimation with fences (lower and upper fences at −3.5 and 3.5, respectively) |
Initial score randomly chosen between −0.5 and 0.5 | |
Limit the estimate jump by 1 for the first 5 items | |
Outputs | Save item use (exposure) |