ABSTRACT
Intuitively, if you have more than one sample, you could potentially do all the possible pairwise two-sample tests. However, there are two problems with this approach. First, the number of tests increases rapidly with the number of samples. For instance, for three samples, there are three possible pairwise tests, for five samples there are ten tests, for ten samples there are 45. Second, the larger the number of tests, the lower the overall power. Let me explain this with a little bit more detail.
