I am using the GLM to model my data. The response variable is binary and there are two predictors, namely, speed (cm/s) and position (cm). First of all I have used the Zernic basis functions to model the position, hence instead of just one predictor as a position, I have bunch of basis functions which the GLM is going to find the coefficient for each of them. I have done the same thing for the speed, only the difference is that instead of the Zernic basis function I have used the Polynomials.
What I want to find is which factor, i.e., speed or position is more important. I have first standardized both speed and position and after applying the GLM I have a few coefficients for the position and some for speed. I somehow want to summarize all the coefficients of the position into one number and the same thing for the speed. In the end whichever is bigger (the absolute value) I would take as the important factor. Any help would be appreciated?
