A Proposed Standard for the Reporting of Structural Equation Models With Ordinal Variables: Why Ordinal Data Should be Treated With Extra Care?

Educational researchers, as well as researchers in other disciplines, often work with ordinal data, such as Likert item responses and test item scores. Critical questions arise when researchers attempt to implement statistical models to analyse ordinal data, given that many statistical techniques assume the data analysed to be continuous. Could ordinal data be treated as continuous data, that is, assuming the ordinal data to be continuous and then applying statistical techniques as if analysing continuous data? Why and why not? Focusing on structural equation models (SEMs), particularly confirmatory factor analysis (CFA), this article discusses an ongoing debate on the treatment of ordinal data and reports a short review on the practices of conducting and reporting SEMs, in the context of mathematics education research. The author reviewed 70 publications in mathematics education research that reported a study involving SEMs to analyse ordinal data, but less than half discussed how data were treated or guided readers through the analysis; it is therefore harder to repeat such an analysis and evaluate the results. This article invites methodological discussions on SEMs with ordinal variables in the practices of educational research. Subsequently, a standard for reporting SEMs with ordinal data is proposed, followed by an example. This standard contributes to educational research by enabling researchers (self and others) to evaluate SEMs reported. The example demonstrates, using real-life research data, how two different approaches for analysing ordinal data (as continuous or as a product of discretisation from some continuous distributions) can lead to results that disagree.