I have a little problem with the results of two of my surveys. The first one is a normal SEM with a rank order for the attribute levels in stage 1 and with a constant sum (100 points) for the attribute importances in stage 2. The second survey is an ACBC that shows part-worths in zero-centered diffs.
Now I would like to normalize the simple part-worths of the SEM into zero-centered diffs to be able to compare the them within the attributes for the two surveys.
Is that somehow possible? And if it is how does it work? I was not able to find any academic article about the calculation of the zero-centered diffs.
Can you help me out please?