A Generalized Objective Function for Computer Adaptive Item Selection

Abstract

AbstractComputer adaptive testing (CAT) is an increasingly common mode of test administration offering improved test security, better measurement precision, and the potential for shorter testing experiences. This article presents a new item selection algorithm based on a generalized objective function to support multiple types of testing conditions and principled assessment design. The generalized nature of the algorithm permits a wide array of test requirements allowing experts to define what to measure and how to measure it and the algorithm is simply a means to an end to support better construct representation. This work also emphasizes the computational algorithm and its ability to scale to support faster computing and better cost‐containment in real‐world applications than other CAT algorithms. We make a significant effort to consolidate all information needed to build and scale the algorithm so that expert psychometricians and software developers can use this document as a self‐contained resource and specification document to build and deploy an operational CAT platform.