I've always been taught that mediator variables should come after your manipulation (your categorical IV) in an experiment. However, I'm now reading this article that says

"The safest ways to make sure your mediator is not caused by your DV are to experimentally manipulate the variable or collect the measurement of your mediator before you introduce your IV." Link to article here

Is this a typo? Why would you want to mediator to come before the IV if you are testing whether the categorical IV has an effect on the mediator variable, which directly affects your DV?


1 Answer 1


I believe this is a typo and "IV" should be changed to "DV". The whole sentence is about the relationship between the mediator and the DV, and the sentence only makes sense with "IV" replaced with "DV". The advice applies in particular to a situation in which the temporal ordering of events is ambiguous because the DV and mediator are measured at the same time. It seems to me that the author is warning against this occurrence and advising researchers to take this problem seriously by measuring or manipulation the proposed mediator before measuring the DV.

  • $\begingroup$ Great that's what I thought too. Just wanted to be sure. Thanks! $\endgroup$
    – Jin
    Aug 12, 2018 at 5:22

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.