Suppose a researcher is developing a scale to measure faculty attitudes toward the use of digital assessment tools in higher education. Although a similar validated scale exists for secondary and higher secondary school teachers, the researcher did not adapt that version. Instead, the items were developed by drawing from an existing student-focused scale, while retaining the same underlying dimensions.
Given that the dimensions are already theoretically supported in previous research, is it necessary for the researcher to conduct an Exploratory Factor Analysis (EFA), or is it methodologically acceptable to proceed directly with Confirmatory Factor Analysis (CFA) to validate the structure in the context of university faculty?
Thanks for knocking me. You can apply both EFA CFA if possible based on your data. Keep in mind that CFA is upper level analysis. At first, you have to complete EFA. Thank you ❤️❤️
You could proceed directly to CFA. Since you have a priori theoretical assumptions about the structure of the scale, there is no need to explore the factor structure using EFA. EFA could be useful, however, if your CFA of the theoretical structure shows substantial misfit. In that case, EFA may help you identify the reasons for the misfit (e.g., substantial cross-loadings of certain items).
I think that the item base is relevant to the applicability of current factors established on a different item base. However Step 1 should be a parallel analysis to determine how many factors to extract because this is the most consequential decision in any factor analysis. Ater that I'd go exploratory with CFA a possible afterthought.
- Badges
- Science topic