- International Journal of Assessment Tools in Education
- Vol: 5 Issue: 4
- Automating Simulation Research for Item Response Theory using R
Automating Simulation Research for Item Response Theory using R
Authors : Sunbok Lee, Youn-jeng Choi, Allan S. Cohen
Pages : 682-700
Doi:10.21449/ijate.472185
View : 13 | Download : 9
Publication Date : 2018-12-16
Article Type : Research
Abstract :A simulation study is a useful tool in examining how validly item response theory (IRT) models can be applied in various settings. Typically, a large number of replications are required to obtain the desired precision. However, many standard software packages in IRT, such as MULTILOG and BILOG, are not well suited for a simulation study requiring a large number of replications because they were developed as a stand-alone software package that is best suited for a single run. This article demonstrated how built-in R functions can be used to automate the simulation study using the stand-alone software packages in IRT. For a demonstration purpose, MULTILOG was used in the example codes in the appendices, but the overall framework of a simulation study and the built-in R functions used in this article can be applied for a simulation study using other stand-alone software packages as well.Keywords : IRT, Simulation, R