Teaching Confirmatory Factor Analysis to Non-Statisticians: A Case Study for Estimating Composite Reliability of Psychometric Instruments.
Byron J. Gajewski, Yu Jiang, Hung‐Wen Yeh, Kimberly K. Engelman, Cynthia S. Teel, Won Sik Choi, K. Allen Greiner, Christine Makosky Daley · PubMed · 2014
its computation. We focus on how to use CFA to estimate a "composite reliability" of a psychometric instrument. This paper provides guidance for introducing, via a case-study, the non-statistician to CFA. As a complement to our instruction about the more traditional SPSS, we successfully piloted the software R for estimating CFA on nine non-statisticians. This approach can be used with healthcare graduate students taking a multivariate course, as well as modified for community stakeholders of our Center for American Indian Community Health (e.g. community advisory boards, summer interns, & research team members). The placement of CFA at the end of the class is strategic and gives us an opportunity to do some innovative teaching: (1) build ideas for understanding the case study using previous course work (such as ANOVA); (2) incorporate multi-dimensional scaling (that students already learned) into the selection of a factor structure (new concept); (3) use interactive data from the students (active learning); (4) review matrix algebra and its importance to psychometric evaluation; (5) show students how to do the calculation on their own; and (6) give students access to an actual recent research project.