Hi all,
My study examines a main IV-DV relationship and how this is moderated by M1, M2 and M3. DV is measured on a 7-point Likert scale; IV, M1-M3 are dummy variables.
Only the main relationship is significant. For the moderating relationships, the direct relationships are significant – corresponding with earlier studies – but not the interaction terms (IV*M1, IV*M2, and IV*M3). The results are confirmed by supplementary analyses and robustness checks.
One possible explanation for the non-significant interaction terms could be the binary coding of the variables, which in itself restricts the variance in interaction terms. Can you suggest how to get around this limitation for a subsequent paper with the same data? Someone suggested that I use vectors and angular separation. Is this compatible with multilevel data?
Thank you.
What stat package are you using? If its SPSS then you have the option of using the 7 points of the likert scale as they are without using binary coding
You seem to be puzzles by the absence of interactions. You could check if there are indications that there should be interactions, by testing for the effect (on the DV) of the dummy variables M1, M2 and M3, each time for both levels of the IV. This could be accomplished by 6 t-tests; 3 (for the effects of M1, M2, and M3) for the first level of your IV and the same 3 for the second level of IV. For example, if there is an effect of M1 (on the DV) at level 1 of the IV, but not at level 2 (or vice versa); this is an indication of the interaction IV*M1.
- Badges
- Science topic