Moderation graphs

darc

New Member
#1
Hi all,

(I hope I'm posting this in the right sub-forum)

I have two data sets for which I've done hierarchical regression analysis to test for interactions (moderation).

In both cases I generated plots in SPSS using the guidelines I found in Aiken & West's book (Aiken & West (1991). Multiple regression: Testing and interpreting interactions.). My plots are the first two images attached to this post.

For anyone here who is familiar with this type of analysis (this is the first time I'm using it), I have two questions:

(1) How should I interpret the values along the Y axis? Should they be regarded as x-mean (i.e., similar to the values of a centered variable)? I'm asking this because in the first graph most values are negative and I'm not exactly sure what to make of them. I apologize if this sounds like a dumb question, but I couldn't find any explicit information about this anywhere.

(2) I did the second graph (second image) using the same method I used for the first one, but as you can see it does NOT look like a moderation graph is supposed to look and I'm not sure why. I checked my equations and they seem correct. I then tried doing the graph with ModGraph and, as you can see in the third image, it looks ok. Has anyone here come across this type of problem before? If yes, what was the error?

Thank you.

Darc