This chapter discusses the implementation of Discriminant Analysis (DA) as a statistical method for reducing the dimensionality and classifying oil spill data according to the chemical properties. DA is a group of oil samples by their chemical composition in order to identify the pollution sources. DA is one of the linear combination input variables, and its effective to be used in oil spill fingerprinting. The readers are able to practice step-by-step analysis of DA using Excel in this chapter, which consist stepwise forward and backward mode. After that, the readers will gain the new knowledge that DA is a powerful tool for dimensionality reduction and classification of oil samples, also enhancing the accuracy of source identification, especially in environmental forensic studies. A statistical method called Discriminant Analysis (DA) was used to group data according to certain characteristics. By examining the correlation between independent variables (features) and dependent variables (group labels), it develops a model that delineates the borders between various groups. Finding a set of discriminant functions or linear feature combinations that optimize the distance between groups is the primary objective. The model was used to forecast the group for recently acquired or unclassified data after trained. In disciplines including biology, business, and environmental science, DA is frequently employed for tasks like source of pollutants identification, market segmentation, and pollutant source tracing.