I am not an expert in statistics, but I was reading a paper that measures correlation relationships and I just stopped by the study design in that paper as it doesn't make sense to me. The problem is that it studies the correlation between x and y, where in fact x is calculated from y such that: x=y+z
My understanding is that when we study correlation relationship, we look into 2 independent variables. So with x=y+z, we already know that they are correlated.
Am I missing anything? any thoughts?