suppression in simple mediation

[Salbod]

Good afternoon.
 
I had suppression occur in a simple mediation analysis (Process 4.0). Can the mediation hypothesis still be discussed or does the suppression effect become the focus of the interpretation? Here is the output:
(C) Total X->Y = -.5439 (p<.05)
(A) X->M = .0892 (p <.001)
(C’) Direct X->Y = -1.2771 (p <.001) and (B) M->Y = 8.220 (p <.001)
(AB) Indirect X->M->Y = .7332 (Boot-CI: .4792, 1.0295l)

Any suggestions will be greatly appreciated. Thank you.

Steve (Pace U-NYC)

[Salbod]

The davidakenny.net site addresses the issue:

Inconsistent Mediation

           If c' were opposite in sign to ab something that MacKinnon, Fairchild, and Fritz (2007) refer to as inconsistent mediation, then it could be the case that Step 1 would not be met, but there is still mediation.  In this case the mediator acts like a suppressor variable.  One example of inconsistent mediation is the relationship between stress and mood as mediated by coping.  Presumably, the direct effect is negative: more stress, the worse the mood.  However, likely the effect of stress on coping is positive (more stress, more coping) and the effect of coping on mood is positive (more coping, better mood), making the indirect effect positive.  The total effect of stress on mood then is likely to be very small because the direct and indirect effects will tend to cancel each other out.  Note too that with inconsistent mediation that typically the direct effect is even larger than the total effect.

I can write up my results in the framework of inconsistent mediation.

[Bruce Weaver]

Hi Steve.  See also MacKinnon et al. (2000).  

MacKinnon, D. P., Krull, J. L., & Lockwood, C. M. (2000). Equivalence of the mediation, confounding and suppression effect. Prevention science, 1(4), 173-181.
https://link.springer.com/content/pdf/10.1023/a:1026595011371.pdf

And for some very thoughtful guidance on how to describe and discuss the results of your mediation analyses, see this article by Klaus Fiedler et al.

Fiedler, K., Harris, C., & Schott, M. (2018). Unwarranted inferences from statistical mediation tests–An analysis of articles published in 2015. Journal of Experimental Social Psychology, 75, 95-102.
https://www.sciencedirect.com/science/article/abs/pii/S0022103117300628

I consider both of these articles essential reading for mediation analysts, and for readers who are trying to understand mediation analyses.  

Cheers,
Bruce

Salbod wrote

The davidakenny.net site addresses the issue:

Inconsistent Mediation

           If c' were opposite in sign to ab something that MacKinnon, Fairchild, and Fritz (2007) refer to as inconsistent mediation, then it could be the case that Step 1 would not be met, but there is still mediation.  In this case the mediator acts like a suppressor variable.  One example of inconsistent mediation is the relationship between stress and mood as mediated by coping.  Presumably, the direct effect is negative: more stress, the worse the mood.  However, likely the effect of stress on coping is positive (more stress, more coping) and the effect of coping on mood is positive (more coping, better mood), making the indirect effect positive.  The total effect of stress on mood then is likely to be very small because the direct and indirect effects will tend to cancel each other out.  Note too that with inconsistent mediation that typically the direct effect is even larger than the total effect.

I can write up my results in the framework of inconsistent mediation.

[Salbod]

Thank you Bruce for the homework. Yes, I love homework. It gives me something to do on rainy weekends.