ABSTRACT
There can be no doubt that the extension of the Rasch model for simple dichotomous data into the rating scale model (Andersen, 1977; Andrich, 1978b) has had an enormous impact o n Rasch modelling. The rating scale model is now used routinely for the analysis of Likert scale data (chap. 6), but Andrich originally intended it for another purpose. It was first intended for use in the evaluation of written essays. It wou ld assist the examination process by producing measures from values applied to qualitative essay rating scales by examiners. However, it also paved the way for all the Rasch models that involve data with more than two values (0, 1).
