Interpreting non-linear ratio

noetsi

Fortran must die
#1
I am discussing this on another thread, or was, but I realized it would get buried and is another topic. I have a series (31) likert scale predictors for logistic regression (so all variables are measured on the same scale). After a lot of consideration I decided to go with odds ratios to rate the relative impact of my predictors. But based on Box Tidwel 5 of my variables are non-linear (two are close in that they are just below .05 on the Box Tidwel test).

The question is how do you compare (can you compare) relative importance of linear and non-linear predictors on the DV. (By importance I mean had the most impact on the DV relative to other variables].
 

noetsi

Fortran must die
#3
Its a simple test. You log the predictor than create an interaction term between the original variable and the logged value. If this is significant in the regression model the original variables relationship is non-linear.

My problem is when ranking the effect size of variables, some of which are non-linear, I do not know how to evaluate the non-linear relationships relative importance. All the literature I know on non-linearity discusses evaluating it through graphs. Not how to evaluate the level of the parameter [I am not even sure you can interpret easily non-linear and linear parameters - but if there is a way to do so in terms of which is most important, I would love to know it].