Is it necessary to do EFA before CFA ? under what circumstances we can skip EFA ?
EFA and CFA have such different assumptions (e.g. factor loadings on all latent measures, or only some), that results are not always replicable or comparable. Try replacing the EFA step with ESEM: that will produce results that you can take forward into CFA much more easily. Here's an intro the ESEM and what it can offer about EFA when you're also thinking ahead to CFA: https://www.statmodel.com/download/SEM-Asparouhov2009.pdf
The decision about using EFA and CFA is not discretionary, rather it depends upon the constructs you are employing in your study. If your model contains constructs that have been not well tested in terms of reliability and validity, you must proceed with EFA in such circumstances before CFA. Otherwise you can use CFA directly if you constructs are well established in literature.
Thanks Mr Hall and Mr Ahmad for your insights .
I am studying buying behaviour of credits by rural Indians . I am using "theory of planned behaviour " which is an established theory to study buying behaviours under different scenarios and the constructs - "attitude" , "subjective norms" and "perceived behavioural control " are established like say attitude = beliefs x values .. I have taken underlying items of beliefs and their corresponding values from existing literature .. I have a model fit during CFA . Do i have some statstical citation for skipping EFA.
If you're already using CFA, but seeking to explore the items (which have not previously had their factor structure documented), then can I again suggest ESEM (providing you're using mplus). That really would be the best solution, and one that I'd recommend to any of my colleagues or postgrad students in the same situation. If ESEM is not available though, then CFA based on TPB sounds interesting. You'd just need to phrase your lit-review, method, and results section using suitable language, e.g. "here a test was carried out of the divisions in psychological constructs present within the TPB".
Dear Sanjeev,
As you are studying buying behavior, the attached file may help..
Article An Easy Approach to Exploratory Factor Analysis: Marketing P...
Hi. I am developing a scale about procrastination on instrumental practise. I have three dimensions. 1. self efficacy, self regulation and third is student's perceptions about thier future carier with their instruments (how long do I need my instrument in my future career). I have previously determined my substances according to these three factors. self efficacy and and self regulations are well tested factors by previous studies but third one is not well tested. should I use EFA before CFA? I am sorry for my english.
Scholars suggest that adopted scales with sufficient empirical and theoretical evidence can be taken directly to CFA without running EFA beforehand (Hurley et al., 1997).
Hurley, A. E., Scandura, T. A., Schriesheim, C. A., Brannick, M. T., Seers, A., Vandenberg, R. J., & Williams, L. J. (1997). Exploratory and confirmatory factor analysis: Guidelines, issues, and alternatives. Journal of organizational Behavior, 667-683.