# How can I test Control variables within a mediation analysis?

In my Masters thesis I do a mediation analysis with Multiple Regression Analysis.

So I make use of the Baron & Kenny method for testing mediation. I also want to control for some variables. For example I want to know if gender has an effect on the mediation effect. What I did was to split the data file(women/ men) (I'm using SPSS 21) and then run the mediation analysis again separately for the two groups. However, if I want to control for age, splitting the file makes no sense. Is there any analytic procedure to test the effect age or any other non categorical variable has on the mediation effect? And if this should be the case, how can I run this analysis in SPSS?

Thank you very much for your help.

Two points:

1) Are you aware of new work on mediation by, e.g., MacKinnon? e.g Annual Review Pschology, this web page and this book?

Eseentially, MacKinnon treats mediation as existing on a continuum rather than being either present or absent (which is what Baron and Kenny's old article does).

2) You can include the covariates in the regression equations and proceed with either approach. There is no need to split the data for the categorical variable.

I can't help with SPSS, but it should be straightforward. If you still have SPSS problems with this, however, the better site is StackOverflow.

In SPSS you can use the PROCESS macro, which is freely available. You would then chose model 4 and add gender as a covariate. You can give a look to this document for further explanation and extension of what PROCESS can do.

Alternatively, if you were to consider a totally free alternative to SPSS, in R you could use the package lavaan. Here there is an example for simple mediation. Here is an example of multiple mediation with a control variable. But this approach might take a bit more time than SPSS