I would like to quantify the difference between two sample sets using KS test. If i apply the test on the original data, the returned p value is less than 1%, but if I bin the set the returned p value is equal to 1. How it is possible? Is it correct binning sample before KS application?
Actually, visualizing the their distributions, I found them similar. I also used a chi square test obtaining the same p value = 1.
I know that normalization makes similar biased normal distributions, but i have simply binned, passing the absolute number for each bin to the KS method.