Factor analysis is a technique used to identify and characterize latent variables (i.e., factors) by examining the relationships among manifest variables. In exploratory factor analysis (EFA), various factor models are considered to uncover the underlying latent structure. Now, the success of EFA lies with the model's interpretability, as the objective is to build a factor model that is not only supported by data, but is also meaningful. Obtaining such a model, however, is challenging, as gauging interpretability is difficult and subjective, owing to rotational indeterminacy. To address this problem, we propose a new interpretability index that measures the interpretability of a factor model. The index does this by evaluating the agreement between a priori information, such as semantic information encoded as semantic similarities among items, and the loadings. Building on this, we also introduce pairwise target rotation or priorimax rotation, which seeks the most meaningful loading matrix by maximizing the index. In general, this method allows for an intuitive yet flexible way of incorporating a priori information, such as semantics, in factor rotations, which can help the researcher perform EFA more effectively. Based on our simulation experiment, the index correctly indicates better fit when noise levels are lower and the priorimax rotation outperforms classical orthogonal rotations across a wide range of conditions in terms of recovering the latent structure. Finally, we applied the index to the Depression Anxiety and Stress Scale (DASS-42) and the Big-Five Factor Markers, providing evidence linking item semantics to latent constructs, consistent with recent findings.

翻译：暂无翻译