When we conduct regression analysis – regardless of the type – we can only analyse x-variables that are continuous (ratio/interval) or binary (i.e. they consist of only two values). A binary variable is sometimes called “dichotomous”, “binomial” or “dummy”. If we have a categorical variable with more than two values, such as in the example in the following sections, we need to “trick” the regression analysis to correctly analyse those variables. To do this, there are two alternatives in Stata. These will be presented next.