The study compared different non-parametric statistical tests to see which one is best for analyzing data when we don't know much about the distributions being tested. The researchers found that tests based on the empirical distribution function (EDF) are more reliable in this situation. However, if we have some prior knowledge about the distributions and expect differences in variance or sparseness, the Chi-squared test might be a better choice. It's also important to adjust for correlation between samples when analyzing data.