A Comprehensive Overview of Ordinal Regression in Statistical Modeling

Ordinal regression or ordinal logistic regression is a statistical technique that makes predictions about an ordinal dependent variable with one or more independent variables. This technique is an extension of both multiple linear and binary logistic regression and is therefore appropriate for the analysis of ordinal outcomes. This method can be used broadly in the social sciences, social work, health care, economics, and any other discipline dealing with data or outcomes that can be categorized in an ordinal fashion in categories of ‘low’, ‘medium’, and ‘high’. References with examples of how to use ordinal regression, including linear and logistic models, and the underlying assumptions are provided in this paper.