Mediation with Structural Equation Modeling....

My question is about how to test mediation with structural equation modeling. I know there is a way to test mediation with regression using a stage successive approach, but some people say it is very better to do mediation using structural equation modeling.

Suppose I say thinking negatively mediates the impact of seeking perfection on depression.

If you are familiar with the regression method, the significance of the direct effect of perfectionism on depression when the indirect effect is included in the model is the determinant of mediation. What about the structural model? How do you test the significance of these paths?

Also How do you test the same model with 2 mediators in the model?


Thank you