I'm not sure...without reading more about his article, it seems to me his examples deal with situations where a fourth hidden factor is introduced between X and Y (e.g., X'). It is likely that c' is not significant due to the existence of X', when M remains a viable mediator between X and Y (i.e., a x b is significant). If so, B & K mediation tests deal with the effect of X on X’, not Y. In that sense, the assumption of a significant c'' (X --> X') still must hold.
I'm not sure...without reading more about his article, it seems to me his examples deal with situations where a fourth hidden factor is introduced between X and Y (e.g., X'). It is likely that c' is not significant due to the existence of X', when M remains a viable mediator between X and Y (i.e., a x b is significant). If so, B & K mediation tests deal with the effect of X on X’, not Y. In that sense, the assumption of a significant c'' (X --> X') still must hold.
vgx2008 2 weeks ago
Very insightful!
ellomellowify 1 year ago