Hi all,

I am trying to analyse a set of data where the DV (called CWV) is continuous (it is the computed average score of three other variables), and has eight IVs (Ability, Prior, Field, Specialty, Backed, Consistency, Trust, and Opinion), each with three levels (Strong, Weak, or NA - coded as 1, 2, or 0). I am trying to analyse the effect of each of the variables' levels on the participants' score (CWV), however, when I run a linear regression it does not break the IVs down by level - only displays the variable as a whole. Would the best option be to run three separate linear regressions, each with the IVs dummy coded into their separate levels (e.g., Ability_Weak, Prior_Weak, etc.)? Or is there another regression analyses that would be better? I had originally attempted a multinomial logistic regression (as it would break it down/present each level in the one table), however, I am not sure if this was the correct choice - or perhaps I am just interpreting it or running it incorrectly!

Thank you in advance, and I apologise for the long winded question!