Computerized Multistage Testing: Principles, Designs and Practices with R

Abstract

ABSTRACTIn recent years, Computerized Multistage Testing (MST), with their versatile benefits, have found themselves a wide application in large scale assessments and have increased their popularity. The fact that forms can be made ready before the exam application, such as a linear test, and that they can be adapted according to the test taker's ability level, such as computerized adaptive tests, has brought MST to the forefront. It is observed that simulation studies are often used in research on MST. The R programming language used in the conduct of simulation studies is widely used for statistical calculation, data visualization, and Monte Carlo research. Researchers can perform their analysis according to their own research questions, both by writing their own code in R and by using the packages in the library. This study aims to demonstrate the design and implementation of MST simulation examples using the R programming language. In this context, first of all, the basic components of MST were discussed, then R packages written on MST were examined in terms of advantages, disadvantages and analysis facility. Then, three different MST simulation examples were designed with the R programming language. It is considered that this study will be useful to those who are interested in MST.KEYWORDS: Computerized multistage testingcomputerized adaptive testingRmonte carlosimulation Disclosure statementNo potential conflict of interest was reported by the authors.