Factors

In statistical data analysis, we often necessary to represent categorical variables: data that fall into of discrete groups or levels. Typical examples include nominal variables like {“male”, “female”}, {“yes”, “no”}, or political party affiliation. In R, we use factors to represent categorical variables in our data.

An R factor is a special kind of object that encodes a categorical variable’s grouping information through in a consistent way that R functions know how to handle. Factors are particularly important for modeling and plotting functions. When we use a categorical variable as part of a statistical model or visualization, the variable needs special treatment to be treated as groupings or levels, rather than as continuous quantities.