Mediation analysis with more than one predictor

Question

I conducted a mediation analysis with 6 predictors, one mediator and one outcome variable. Now I am trying to write up the results but I am not quite sure how to structure my report... (e.g.: write about total effects for all predictors, then direct effects for all and so on vs. write about one predictor (all its effect) at a time).

Can anyone recommend APA-conform research reports about a similiar analysis?

Thanks!

Answer 1

I'm going to assume that you are running a series of simple mediation models -- one for each of your predictor variable (X1-X6). If so, then you could present the result of your mediation analyses in a single table and write about them in the results section one predictor at a time. For example:

"The indirect effect of X1 via Mediator is statistically significant (ab = 0.##, 95% CI [0.##, 0.##])." The direct effect is also significant (b = 0.##, SE = 0.##).

It would look something like Table 4 in Ma and Grogan-Kaylor (2017) except you would be grouping by independent variables as opposed to dependent variables.

Alternatively, I suppose you could show your findings in a series of figures like Stellar et al. (2018) - Figure 2. However, since you have so many X variables, I think this would be less efficient than putting everything into one table.

References

1. Ma, J., & Grogan-Kaylor, A. (2017). Longitudinal associations of neighborhood collective efficacy and maternal corporal punishment with behavior problems in early childhood. Developmental psychology, 53(6), 1027.
2. Stellar, J. E., Gordon, A., Anderson, C. L., Piff, P. K., McNeil, G. D., & Keltner, D. (2018). Awe and humility. Journal of personality and social psychology, 114(2), 258.