The Kolmogorov–Smirnov (KS) test is one of many goodness-of-fit tests that assess whether univariate data have a hypothesized continuous probability distribution. The most common use is to test whether data are normally distributed. Many statistical procedures assume that data are normally distributed. Therefore, the KS test can help validate use of those procedures. For example, in a linear regression analysis, the KS test can be used to test the assumption that the errors are normally distributed. However, the KS test is not as powerful for assessing normality as other tests such as the Shapiro–Wilk, Anderson–Darling, and Bera–Jarque tests that are specifically designed to test for normal distributions. That is, if the data are not normal, the KS test will erroneously conclude that they are normal ...
Looks like you do not have access to this content.