Hi there, I definitely do need your help!!! Looking through studies and books I got a little confused by the different approaches used to conduct factor analyses for reflective scales before running PLS-analysis. Some recommend carrying out exploratory factor analysis (EFA) using SPSS first, followed by covariance-based confirmatory factor analysis (CB-CFA) using e.g. AMOS. The "stepwise" received results (items) are then applied to PLS for further analyses. Others are pro EFA (in SPSS) but advice against using CB-CFA (e.g. AMOS) before PLS-analysis, criticizing they have different underlying assumptions. Instead they recommend doing the CFA directly in PLS (using the EFA's results). But even within the field of EFA there seems to be some confusion about what extraction method (principal component vs. principal axis vs. ...) and which rotation procedure (oblique vs. Varimax) are most appropriate when using PLS afterwards. So, my question: Are there any rules or is there a generally accepted way of how to conduct EFA and CFA when using PLS? Could you provide me with corresponding references (published articles etc.)? Hope, someone can help! Thanks in advance!
Yinan Li You may check the following my papers in terms of EFA, CFA, and SEM. I have used different approaches and different software (Amos/SmartPLS) to analyze the data, you can find the full text in my researchgate.
1. She, L., Rasiah, R., Turner, J.J., Guptan, V. and Sharif Nia, H. (2021), "Psychological beliefs and financial well-being among working adults: the mediating role of financial behaviour", International Journal of Social Economics, Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/IJSE-07-2021-0389.
2. She L, Ma L, Jan A, Sharif Nia H and Rahmatpour P (2021) Online Learning Satisfaction During COVID-19 Pandemic Among Chinese University Students: The Serial Mediation Model. Front. Psychol. 12:743936. doi:10.3389/fpsyg.2021.743936
3. She, L., Rasiah, R., Waheed, H. and Pahlevan Sharif, S. (2021), "Excessive use of social networking sites and financial well-being among young adults: the mediating role of online compulsive buying", Young Consumers, Vol. 22 No. 2, pp. 272-289. https://doi.org/10.1108/YC-11-2020-1252
4. Sharif Nia, H., Pahlevan Sharif, S., She, L., Sivarajan Froelicher, E., Kaveh, O., & Rahmatpour, P. The relationship between abusive supervision, psychological ownership, and quality of nursing care: The mediating role of job satisfaction. Perspect Psychiatr Care. 2021; 1- 9. https://doi.org/10.1111/ppc.12919
Hello Yinan,
I have only taken one class in SEM. My instructor pointed out that, in theory, you are always doing a Confirmatory Factor Analysis to some extent because if you didn't have an idea of what to expect, you wouldn't be looking. I recall that Ortoginal rotation is the default in most programs, and this assumes that the factors are uncorrelated, in contrast to oblique, where correlated factors are assumed.
I was advised to use either the principal axis maximum likelihood method, avoid the Keiser Gutman rule selecting eigenvalues greater than one in favor of examining the scree plot and including the factors above the "elbow "on the plot. I don't have much experience with AMOS as Mplus can also produce path models. Here is a link to a detailed breakdown of the topic and other subtopics likely to be helpful. I only recently started using this forum, but I am glad to have so many exciting projects to follow, Good Luck!
http://web.pdx.edu/~newsomj/semclass/ho_efa.pdf
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS