Linear Regression - variable issues!

#1
Hi there,

I am trying to run a linear regression on some data to investigate a mediating relationship. There are three variables: whether or not training was provided (IV), social skills (DV) and hours of self-study (MediatorV).
My IV has two levels represented as 0 (control) and 1 (training provided) however when I put the variable as a whole into SPSS for analysis it comes out showing both training and control together, and I need to see their separate effects.
I've looked into dummy coding them but I am still unsure how to proceed.
Any suggestions would be greatly appreciated!
Thank you.

P.S. I have attached the correlation box from my output to show how it is being shown as one variable (whether or not treatment has been provided).
 
Last edited:
#2
You say you want to see their separate effects, but I'm not totally sure what you mean. Also, how are you seeing self-study as a mediation variable? If you're using linear regression, it seems more like a control variable to me, but I may not be understanding what you're doing here.

When you run the regression, entering the treatment and self-study variables regressed on social skills, the coefficient on the treatment term gives you the treatment effect.

So if the coefficient on that term is 2.1 for example, you would say that on average participants in the treatment group scored 2.1 points higher on the social skill measure when controlling for self-study. So that should give you group differences as I see it.