Unival: An FA-based R package for assessing essential unidimensionality using external validity information

Abstract

The unival package is designed to help researchers decide between unidimensional and correlatedfactors solutions in the factor analysis of psychometric measures. The novelty of the approach is its use of external information, in which multiple factor scores and general factor scores are related to relevant external variables or criteria. The unival package's implementation comes from a series of procedures put forward by Ferrando and Lorenzo-Seva (2019) and new methodological developments proposed in this article. We assess models fitted using unival by means of a simulation study extending the results obtained in the original proposal. Its usefulness is also assessed through a real-world data example. Based on these results, we conclude unival is a valuable tool for use in applications in which the dimensionality of an item set is to be assessed.