Hello Tariq,
You might be thinking of mediation ("intermediate variable") vs. moderation ("interactive variable").
For mediation, consider the relationships: (a) X -> M -> Y and (b) X -> Y.
The first case (a) specifies that the independent variable, X, influences the dependent variable, Y, in an indirect way, via M. The second case (b) specifies that the IV directly influences the DV. If the indirect path (a) is shown to be noteworthy, that is evidence of at least partial mediation. In the case that path (b) is not distinguishable from zero, then you have evidence for complete mediation (assuming some indirect effect, of course).
For moderation, consider the model Y-estimated = intercept + X + M + X*M. To the degree that the interaction (X * M) is noteworthy, you have evidence for moderation (e.g., the influence of X on Y is moderated by the level of M; in other words, the specific level of X and specific level of M jointly influence the level of scores on the DV, above and beyond the overall effect of X alone or M alone).
Andrew Hayes' text is an excellent source for more detailed explanation of these topics, so if you're interested you might have a look at it: Introduction to mediation, moderation, and conditional process analysis: A regression-based approach (now in 3rd ed). Guilford Press.
Good luck with your work.
Tariq Kadhim See also Baron & Kenny's (1986) famous article on the mediator-moderator distinction:
Baron RM, Kenny DA. The Moderator-Mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of Personality and Social Psychology. 1986;51:1173–1182.
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.917.2326&rep=rep1&type=pdf
- Badges
- Science topic
- Similar topics
- Biological Science
- Physiology
- Physiological Processes
- Stress