Font Size:
Exploratory factor analysis of ordinal variables: a copula approach
Last modified: 2017-05-20
Abstract
Exploratory factor analysis attempts to identify the underlying factors that explain the pattern of correlations within a set of observed variables. The analysis is almost always performed with Pearson's correlations even when the data are ordinal, but this is not appropriate since they are not quantitative data. The use of Likert scales is increasingly common in the field of social research, so it is necessary to determine which methodology is the most suitable for analysing the data obtained as such data are often analysed using techniques designed for quantitative measures. In this context, and by means of simulation studies, we aim to illustrate the advantages of using Spearman's grade correlation coefficient on a transformation operated by the copula function rather than Pearson correlation to perform exploratory factor analysis of ordinal variables. Moreover, by using the copula, we consider the general dependence structure, providing a more accurate reproduction of the measurement model.