As the name implies, Discriminant Correspondence Analysis (DCA) is a format of Discriminant analysis (DA) and correspondence analysis (CA). Like differential analysis, the goal is to categorize observations into predefined groups and, like Correspondence analysis, to use nominal variables. The main idea of the DCA is to represent each set of observations and perform a simple Correspondence analysis on the variables (a matrix). The main observations are complementary elements, and each observation is attributed to the closest group. A comparison between the predictions and predictions of classification leads to evaluating the Discriminant correspondence. This information can be used for a similar case to classify new observations, and the validation of estimates can also be examined using cross-validation techniques such as Jack Knife or Bootstrap. For example, samples were taken from different regions. After scoring the parameters and training in this analysis, a new sample was entered, and a group (region) was determined compared to the previous samples.