Data that do not have a normal distribution do not have values distributed in a bell-shaped curve. Therefore, for the analysis of these data, parameters such as mean and standard deviation cannot be used for comparison between populations, since the data distribution does not obey the expected mathematical relationships with the mean and standard deviation.

When quantitative data are normally distributed, the tests used for statistical analysis are called parametric tests (based on parameters such as mean and standard deviation). When the data are qualitative or quantitative without normal distribution, non-parametric tests are used (they do not use statistical parameters).