There are three hypotheses and I carry out direct effect and indirect effects with SEM.
H1: There is a significant positive relationship between A and B. H2: There is a significant positive relationship between C and B. H3: C has an indirect effect on the relationship between A and B.
In this case, I know that my H3 hypothesis must be an indirect effect on my SEM outputs. So do I need to report the direct effect or the total effect for my H1 hypothesis? I'm very confused about this.
Note: I don't use Baron and Kenny (1986) for mediation analysis. I test my hypotheses according to contemporary mediation (Hayes, Rucher, MacKinnon et al.). I create a single model and test all hypotheses simultaneously.
Fatih Celik It would be better to report direct, indirect, and total effects for hypothesized paths. You can refer to the article below.
Imran Anwar first of all, thank you very much.
As far as I understand from your study, you evaluated the direct effect (.187 ***) for H4. You presented the total effect as an information rather than a hypothesis test. In this case, the answer to my question is the direct effect.
Fatih Celik For your H1 and H2, you need to report direct effects while for H3, you have to report the indirect effect of A on B via mediating effect of C.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Structural Equation Modeling