0
$\begingroup$

I'm currently facing a challenge and would greatly appreciate your assistance. I'm attempting to conduct a mediation analysis with two mediators in a within-subject design exoeriment using R. Here's a brief overview of my situation:

Research Problem: I'm investigating the relationship between an independent variable (which can take on values of green, yellow, or red) and a single dependent variable.

Mediation Analysis: My analysis involves two mediators, and I want to understand how these mediators influence the relationship between the independent and dependent variables.

Previous Attempts: Initially, I tried using the PROCESS function in R for mediation analysis. However, I encountered difficulties as the function doesn't account for repeated measures, which is essential in my study design.

Current Approach: Upon further exploration, I discovered the mediation package. While this function seems promising for handling repeated measures, I'm unsure if it can accommodate analyses with two mediators. Similarly, I'm uncertain about the capabilities of the lameer function in this context.

I would be immensely grateful if you could guide how to proceed with this analysis. Any insights or recommendations on suitable R packages or methods for conducting mediation analysis with two mediators, particularly in a study with repeated measures, would be incredibly valuable.

Thank you very much for considering my request. Your expertise and assistance are greatly appreciated.

$\endgroup$
1
  • $\begingroup$ If you need help performing a data analysis, you should ask for help at Cross Validated instead where statistical questions are on topic. You are likely to get better help there. This is not really a specific programming question that's appropriate for Stack Overflow. $\endgroup$
    – MrFlick
    Commented Mar 26 at 14:41

1 Answer 1

1
$\begingroup$

If you have two time measures you can use the within-participant mediation approach describes in

Montoya, A. K., & Hayes, A. F. (2017). Two-condition within-participant statistical mediation analysis : a path-analytic framework. Psychological Methods, 22(1), 6-27. https://doi.org/10.1037/met0000086.

You have to use the differences between mediators at the two times measures as the "usual" mediator.

$\endgroup$
2
  • $\begingroup$ Thank you for the suggestion, however, I am not sure if this approach is suitable for me. In my case this is what I am looking for x-> m1 ->y and x -> m2 ->y. The paper is mentioning some like: x->m1 -> y and m2 ->y (without the x->m2 part). $\endgroup$
    – nnjava
    Commented Mar 26 at 16:44
  • $\begingroup$ You have to compute the differences for both mediators and add both in the mediation model so that x>d_m1>d_m2>y. $\endgroup$
    – POC
    Commented Mar 26 at 17:41

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.