0

I got a revision for my research paper recently and the following is the reviewer's comment on my paper: the authors should show that for any estimate from the linear regression that is reported in this manuscript, none of the other variables in the model were potential mediators. If there are potential mediators, then several models should be conducted to ensure none of the estimates are over adjusted.

My question：How can I show that none of the other variables in the model were potential mediators. What statistical analysis should I perform to validate this point?

zhiheng yi
  • 45
  • 4

1 Answers1

1

In path analysis (e.g., using lavaan in R), you can examine several mediators simultaneously. That way, you can examine which indirect effects are meaningful and which are not.

Christian Geiser
  • 3,531
  • 1
    In case you prefer a simpler method, you could also check whether the partial correlation between x and y, partialling out the potential mediator, is substantially different from the zero-order correlation. – rolando2 Feb 27 '24 at 16:16
  • Thank you. If the variables to be adjusted include binary variables, can partial correlation analysis be used? – zhiheng yi Feb 29 '24 at 05:34