Dear friends, My model includes 6 constructs. 2 independent constructs, one dependent construct and 3 mediators. My hypotheses include the relationship between each construct and the mediating effects. Can I run SEM for each pair of constructs separately or single SEM for all constrcuts simultaneously to test the hypotheses?
Thaneswary, generally, the constructs are correlated. If this is the case, separate analyses would not provide information about the unique contributions of the variables on the dependent variable. Therefore, a single model would be preferable. Of course you need to decide about the relationships between the mediator variables. Does your theory support directed effects or not? If you do not have a theoretical basis for deciding on the relationships between the mediator variables, then you need to let the unexplained parts of these variables be correlated.