I am studying influence of Organizational Culture on Employee Engagement where Job Crafting is mediating between culture and engagement. While using SEM, the model is recursive. This relationship is evident in the theory.
If this relationship is reversed where Engagement influences Culture, then the SEM shows non-recursive model.
Shall I continue with the recursive model? In the literature the reverse relationship hardly exist but need to test this as one of the doctoral committee member (statistician) has a different view on my research framework.
In a basic research study, It is absolutely appropriate (and mandatory i will say) to follow what prevailing theory and logic supports, because most often a basic deductive researcher try to find theory generalization rather than sampling generalization of a particular population of interest. Moreover, in my view point, data received through survey responses comprise only of numbers and any statistical tool is just a mean to apply certain types of analysis; only theoretical logic (theory and relevant literature) provide directions and connections of our proposed study variables to, of course, test the deductive logic on a particular sample from a specific population.
Some references might be helpful in understanding the same. Tq
Memon, M. A., Ting, H., Ramayah, T., Chuah, F., & Cheah, J.-H. (2017). A Review of the Methodological Misconceptions and Guidelines Related to the Application of Structural Equation Modeling: A Malaysian Scenario. Journal of Applied Structural Equation Modeling.
Seddon, P. B., & Scheepers, R. (2012). Towards the improved treatment of generalization of knowledge claims in IS research: drawing general conclusions from samples. European Journal of Information Systems.
You can check the reversed model in PLS. AMOS is direction sensitive.
Moreover, it also depends on how the data was collected. It means, while collecting the data what was your IV and DV that matters a lot. If you were to check the relationship in both the direction, the data collection should also follow that intention.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Structural Equation Modeling