Computerized adaptive testing (CAT) is a set of techniques developed to increase the efficiency of testing. Its use, while still in its childhood, is well past its infancy. We now know enough to be able to use it in operational programs. Despite attempts to make CAT as compatible as possible with existing testing practices and procedures, there remain enough subtle differences between an adaptively and a linearly administered test that some loud cautions must be sounded. This note is meant to serve that purpose. We will discuss four practices which are commonplace in traditional testing but which are less sensible within CAT. These practices represent possible potholes on the road to the conversion of a linearly administered test to its adaptively administered successor. We also suggest some ways to avoid these potholes and hence smooth the transition to CAT.
No takes yet. Share an insight, caveat, or question.
Howard Wainer (1992) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: