

The KolmogorovSmirnov test is a nonparametric test that compares the distributions of two unmatched groups.
The KolmogorovSmirnov test works by comparing the cumulative frequency distributions of the two groups.It does not account for any matching or pairing. If the data are paired or matched, consider using a Wilcoxon matched pairs test instead.
Use the KolmogorovSmirnov test only to compare two groups. To compare three or more groups, use the KruskalWallis test followed by post tests. It is not appropriate to perform several KolmogorovSmirnov tests, comparing two groups at a time without doing some correction for multiple comparisons.
By selecting a nonparametric test, you have avoided assuming that the data were sampled from Gaussian distributions, but there are drawbacks to using a nonparametric test. If the populations really are Gaussian, the nonparametric tests have less power (are less likely to give you a small P value), especially with small sample sizes.
The KolmogorovSmirnov test compares two cumulative frequency distributions. Prism creates these distributions from raw data. Prism cannot run the KolmogorovSmirnov test from distributions you enter, only from raw data entered into two columns of a Column data table.