Ordinal Regression Analysis: Fitting the Continuation Ratio Model to Educational Data Using Stata

Ordinal data are widely available to educational researchers. One of the most commonly used models to analyze ordinal data is the proportional odds (PO) model, which is also known as the cumulative odds model. However, when the research interest is focused on a particular category rather than at or below that category, given that an individual must pass through a lower category before achieving a higher level, the continuation ratio model (Fienberg, 1980; Hardin & Hilbe, 2007; Long & Freese, 2006) is a more appropriate choice than the proportional odds model. The purpose of this paper was to demonstrate the use of the continuation ratio (CR) model to analyze ordinal data in education using Stata, and compare the results of the CR model with the PO model. Ordinal regression analyses are based on a subset of data from the ELS (Educational Longitudinal Study): 2002, in which the ordinal outcome of students’ mathematics proficiency was predicted from a set of students’ classroom practices