In simple mediation analysis using Hayes' process for SPSS, the total effect isn't significant, but the IC for the indirect effects are. Can I conclude mediation?
There are many approaches to test mediation and other intervening variable effects. It would be more appropriate to call "indirect effect" in your case. Refer to the following article.
MacKinnon, D. P., Lockwood, C. M., Hoffman, J.M., West, S. G., & Sheets, V. (2002). A comparison of methods to test mediation and other intervening variable effects. Psychological Methods, 7,83–104. doi: 10.1037/1082-989X.7.1.83
There are many approaches to test mediation and other intervening variable effects. It would be more appropriate to call "indirect effect" in your case. Refer to the following article.
MacKinnon, D. P., Lockwood, C. M., Hoffman, J.M., West, S. G., & Sheets, V. (2002). A comparison of methods to test mediation and other intervening variable effects. Psychological Methods, 7,83–104. doi: 10.1037/1082-989X.7.1.83
yes after Preacher and hayes
At odds with Baron & Kenny they posits that significant direct efecct are not necessary
look at thei papers
Dear Joaquin,
you can enlarge your knowledge about these issues by reading a bit about structural equation modeling and especially path tracing. The total effect results from the sum of all indirect effects and a potential direct effects. It's not mysterious at al that if an indirect effect and a direct effect are of opposite direction, the resulting total effect is smaller or even non-significant.
If you call the indirect effect still call "mediation" depends on your definition of "mediation". If you follow the Baron/Kenny thinking, there must be an overall relationship that is mediated somehow. Hence my aforementioned scenario implies no mediation despite a significant indirect effect. If, however, you equate mediation by the existence of a indirect effect, it is still there - although there is no overall effect.
HTH
Holger
One kind of mediation is called "inconsistent mediation." A total may not be significant in the inconsistent mediation.
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2819361/
Have a look on the attached file, it may help...
Article Making Sense of Mediating Analysis: A Marketing Perspective
Zhao et al. (2010) provides a typology of mediations and nonmediations that I find useful and sensible.
Zhao, X., Lynch, J. G., & Chen, Q. (2010). Reconsidering Baron and Kenny: Myths and Truths about Mediation Analysis. Journal of Consumer Research, 37(2), 197–206. http://doi.org/10.1086/651257
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS