Visualizing Multiple Results from Nonlinear CUB Models with R Grid Viewports

Nonlinear CUB models have been recently introduced in the literature to model rating or ordinal data. They extend the standard CUB (Combination of Uniform and Binomial), which is a mixture model combining a discrete Uniform and a Shifted Binomial random variables. Unlike CUB, Nonlinear CUB models account for the unequal spacing among response categories. Nonlinear CUB can be effectively used in a variety of fields, for example whenever questionnaires with questions having ordered response categories are used to measure human perceptions and attitudes. This paper proposes a new graphical representation, which works with R grid Viewports in order to summarize multiple results from Nonlinear CUB models in a unique plot. A case study on the perceived risk in fraud management is presented.