Multidimensional Computerized Adaptive Testing in a Certification or Licensure Context

Publisher Website
Google Scholar
Abstract
Multidimensional item response theory (MIRT) com puterized adaptive testing, building on recent work by Segall (1996), is applied in a licensing/certification context. An example of a medical licensure test is used to demonstrate situations in which complex, integrated content must be balanced at the total test level for va lidity reasons, but items assigned to reportable subscore categories may be used under a MIRT adaptive paradigm to improve the reliability of the subscores. A heuristic optimization framework is outlined that gen eralizes to both univariate and multivariate statistical objective functions, with additional systems of con straints included to manage the content balancing or other test specifications on adaptively constructed test forms. Simulation results suggested that a multivariate treatment of the problem, although complicating some what the objective function used and the estimation of traits, nonetheless produces advantages from a psycho metric perspective.

This publication has 18 references indexed in Scilit: