I am performing a moderated mediation as shown below. In this particular example, this is depicted as a "second-stage moderated mediation". According to Muller et. al. 2005, moderated mediation occurs when moderation of one of the paths is significant (in this case b3); but according to Hayes 2015 one can compute the index of moderation for more direct evidence (a1b3).

Turns out, in my analysis, the conditional indirect effect was significant (a1b3 path). I can claim a moderated mediation. I further probed the mediation at difference levels of the moderator. This yielded the following results: significant estimate at low value (1SD below) but not significant at medium or high values. I am confused at what my conclusions can be? We know there is moderated mediation; but what are the takeaways from this further probing?

Lastly, and this may require a separate question, but what is the difference between simple slopes and conditional indirect effect (as I have just explained). I would like to depict simple slopes for the moderating relationship (in this case between loneliness on PTSD-Depression) but this is not the same as the conditional indirect effect, correct?

enter image description here


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.