Data with 40 items is simulated based on the Nominal Response IRT Model (Bock, 1972). Each variable (column) represents an item and is a "character" variable. This is necessary to be able to run the
CopyDetect2 function. The items are assumed to have five response alternatives: A, B, C, D, and E.
The item parameters used to generate data are taken from Wollack's study (1996).
A data frame with 500 hypothetical simulees.
Wollack, J.A.(1996). Detection of answer copying using item response theory. Dissertation Abstracts International, 57/05, 2015.
Bock (1972). Estimating item parameters and latent ability when responses are scored in two or more nominal categories. Psychometrika, 37, 29-51 .