I was wondering about generally how I should go about and run my multiple regression. I have two independent variables:
- group (binary scored as 0 and 1)
- activity (a continuous variable)
If I run a simple regression on this, both my dependent variables are significant. (y=a+b)
I want to check the interaction effect between the two independent variables on my one continuous dependent variable.
What I have done in SPSS so far is simply create another term with Compute Variable, namely group * activity
Now, when I a run a regression with this interaction variable added (y=a+b+ab) , the main effects of group and activity are not significant anymore, as is the interaction effect.
I was wondering what the difference in interpretation was between running a model as (y=a+b+ab) or simply as (y=ab), because the last option is again significant. Could you help me with the interpretation of these tests?