Analyzing nominal and ordinal categorical responses using item response models and proportional odd models

Abstract

An attitude survey towards divorce was administered to Maltese University students in order to obtain a more comprehensive picture of how University students perceive divorce issues. A number of items describing behaviors and mishaps that may lead to divorce were rated on a 4-point Likert scale by the participants to assess how much they agree with them. Two statistical models were fitted to relate the rating responses to the predictors, mainly, the Proportional Odds model and Item Response Theory model.