부산대학교 도서관

Exploratory and confirmatory factor analyses are commonly employed to identify and explore underlying factor structures. Unfortunately, when variable selection is involved, results often fluctuate across studies making it difficult to determine the "best" and most replicable factor structure. This study proposes a new factor analysis variable selection algorithm called the Replicable Factor Analytic Solutions (RFAS) that incorporates sound statistical and psychometric practices when selecting the final factor structure, while simultaneously examining the observed variables and factor structures replicability. This article outlines the algorithm development and rationale for each decision in the algorithm's development. An example using simulated and empirical data is also provided to display the algorithm results and delineate the utility of these results for future analysts. [ABSTRACT FROM AUTHOR]