We have two measures X and Y that we apply on each class 30 times as follow:
Class X Y A 0.25 0.6 A 0.3 0.4 B 0.6 0.2 B 0.8 1
For simplicity, I just showed two runs (out of 30) for each class. The number of classes that we are testing is 331. This results in the 9930 points in the following plot:
Note that observations from class A might have a similar behaviour when compared to observations from the class B.
We want to know whether there is a correlation exists between measure X and Y for all the classes. Is the spearman correlation helpful in this scenario?