The article compares different ways to test if two sets of data come from the same distribution. The researchers found that the Kolmogorov-Smirnov test can be seen as a way to test equality at each point in the distribution. They also developed a new method that spreads out the power of the test more evenly across the distribution, improving sensitivity to differences in the tails of the data. Additionally, they created a quick way to compute the test for one set of data. By using stepdown and pre-test procedures, they were able to increase the power of the test. Finally, they extended their findings to different types of data distributions and designs.