Ordinal regression: A review and a taxonomy of models

Ordinal models can be seen as being composed from simpler, in particular binary models. This view on ordinal allows to derive a taxonomy of that includes basic regression models, with more complex parameterizations, the class hierarchically structured and recently developed finite mixture The overview is given covers existing shows how extended account for further effects explanatory variables. Particular attention modeling additional heterogeneity as, example, dispersion effects. embedded into framework response styles exact meaning terms investigated. It shown crucially determined by type model used. Moreover, it demonstrated category-specific effect structure simplified obtain simpler fit sufficiently well. fitting illustrated use real data set, short software given. article categorized under: Statistical Models > Fitting Data: Types Structure Categorical Data Generalized Linear