The partial credit model (PCM) is a model for constructing measures using items with two or more ordered response categories; that is, items scored polytomously. The model is a simple application of Rasch's model for dichotomies. Specifically, if responses to item i are recorded in categories a = 0, 1, … Ai, then the probability of a person's response to item i being in category x rather than in category x − 1 is modeled by the PCM, as being governed by Rasch's model for dichotomies.