Analysis of an indirect (mediated) moderation model

The main purpose of this research is to investigate an integration of mediation and moderation. When the effect of X on Y is moderated by Z, does this moderating effect still exist when we include another moderator W, which is related to Z. In contrast to a mediated effect being moderated in current integrated models, here the moderating effect is mediated. We simulated and analyzed data using R under several conditions and checked the times the moderation by Z was actually mediated by W. We set up a four step decision-tree which guides the user trough the steps of the regression analyses in order to infer or refute mediated moderation.