Mediation analysis (Total indirect effects)
Posted: Sat Dec 23, 2023 12:05 am
Dear all,
I need some advice for my mediation analysis. In my research model, there are 2 IVs, 2DVs, and 1 mediator.
To conduct the analysis, I perform the following steps:
1. Build the inner model by putting all the variables into the diagram.
2. Build the outer model by putting all indicators of each variable.
3. Connect all variables by drawing the arrows from 2 IVs --> mediator, and from mediator --> 2DVs. No arrow from IVs --> DVs.
4. Run the path-modeling estimation by selecting “PLS Algorithm".
5. Check outer model loadings and significance, indicator reliability, internal consistency reliability, convergent validity, and discriminant validity. The results show that everything is OK.
6. Check structural path significance in bootstrapping. The results show that all paths are significant.
7. I conclude that the model is correct, the mediator mediates the effects of all IVs on DVs.
The total indirect effect between IVs and DVs is significant in results, but when I connect IVs with DVs to check the association between them, the path coefficients between IV and DV becomes insignificant.
My questions are:
Q1: I want to know the concept behind these results, why there is difference in the total indirect effect results (without connecting IV to DV) and path coefficient results (with connecting IV to DV), as both represents same relationship.
Q2: Is it appropriate to consider IV to DV (total indirect effect results) without connecting IV to DV for exploring relationship between IV to DV in a mediation model.
Your advice and suggestions are greatly appreciated.
Thank you very much.
I need some advice for my mediation analysis. In my research model, there are 2 IVs, 2DVs, and 1 mediator.
To conduct the analysis, I perform the following steps:
1. Build the inner model by putting all the variables into the diagram.
2. Build the outer model by putting all indicators of each variable.
3. Connect all variables by drawing the arrows from 2 IVs --> mediator, and from mediator --> 2DVs. No arrow from IVs --> DVs.
4. Run the path-modeling estimation by selecting “PLS Algorithm".
5. Check outer model loadings and significance, indicator reliability, internal consistency reliability, convergent validity, and discriminant validity. The results show that everything is OK.
6. Check structural path significance in bootstrapping. The results show that all paths are significant.
7. I conclude that the model is correct, the mediator mediates the effects of all IVs on DVs.
The total indirect effect between IVs and DVs is significant in results, but when I connect IVs with DVs to check the association between them, the path coefficients between IV and DV becomes insignificant.
My questions are:
Q1: I want to know the concept behind these results, why there is difference in the total indirect effect results (without connecting IV to DV) and path coefficient results (with connecting IV to DV), as both represents same relationship.
Q2: Is it appropriate to consider IV to DV (total indirect effect results) without connecting IV to DV for exploring relationship between IV to DV in a mediation model.
Your advice and suggestions are greatly appreciated.
Thank you very much.