Objective: Categorical Principal Component Analysis (CATPCA) is a multivariate statistical analysis method used to reveal the correlations between independent variables that affect the dependent variable, as well as dimension reduction and visualization. In the literature review, in this study, since there is almost no Turkish literature on the subject; It is aimed to explain the method with depression dataset and to show its usability in such datasets with an application. Method: In the method, after determining component loads for each dimension in multiple nominal and multiple non-nominal variables, eigenvalues and total explained variance are calculated. In the study, data obtained from 664 students through questionnaires were used. Results: Variables thought to be associated with depression; As a result of reducing to two dimensions with dimension reduction; The variance explanation rate for the first dimension was found to be 18.08% and the variance explanation rate for the second dimension was found to be 16.58%. Conclusions: In Categorical Principal Component Analysis, categorical variables are digitized with various transformations and the loss function allows the application of multivariate analysis methods. Thus, relationships in real space with minimum loss can be shown in a lower dimensional space. In this study, linear and nonlinear relationships between variables are modeled. Accordingly, it was found that there was a relationship between depression and the variables of gender, age, income and department.