I am working on a mediation analysis Using the Sobel's test, I am studying the mediating role of B in the relationship between A & C. So far, I have these regression results:
(A --> B): significant
(B --> C): significant,
(A --> C): not significant.
Upon using the Sobel test equation, the z-score was significant, suggesting a mediating role of B in the relationship between A&C.
the question is: do you think Bootstrapping is necessary in such a case?
I was reading about it in the past days and i noticed that most researchers recommends bootstrapping
However check this
https://www.researchgate.net/post/Why_both_bootstapping_and_Sobel_tests_are_applied_in_some_studies
No. It isn't required if both A -> B and B -> C are statistically significant. This is arguably a better approach for testing mediation (in terms of controlling Type I error at alpha) than bootstrapping. Bootstrapping gives you a CI for the indirect effect which may be useful.
See:
Yzerbyt, V., Muller, D., Batailler, C., & Judd, C. M. (2018). New recommendations for testing indirect effects in mediational models: The need to report and test component paths. Journal of Personality and Social Psychology, 115(6), 929–943. doi: 10.1037/pspa0000132
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size