Normality only really makes sense for continuous variables. For categorical variables (dependent on your application) is often better to aim for a close to uniform distribution so that there are fewer rare categories
@Hayatun @Jamie has rightly said that categorical data are not from a normal distribution. The normal distribution only makes sense if you're dealing with at least interval data, and the normal distribution is continuous and on the whole real line. If any of those aren't true you don't need to examine the data distribution to conclude that it's not consistent with normality.
Normality tests are typically used to check if a continuous variable is normally distributed. Categorical variables are not continuous and therefore cannot be normally distributed.
However, you can still check the distribution of categorical variables using frequency tables and bar charts.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Graphs