Subject choice in educational data sets by using principal component and procrustes analysis

Principal component analysis (PCA) is a dimension-reducing technique that replaces subjects in a multivariate data set by a smaller number of derived subjects. Dimension reduction is often undertaken to help in describing the data set, but as each principal component usually involves all the original subjects, interpretation of a PCA result can still be difficult. One way to overcome this difficulty is to select a subset of the original subjects and use this subset to approximate the data. On the other hand, procrustes analysis (PA) as a measure of similarity can also be used to assess the efficiency of the subject selection methods in extracting representative subjects. In this paper researcher evaluate the efficiency of four different methods, namely B2, B4, PCA-PA, and PA methods. Researcher applies the methods in assessing the academic records of higher secondary students which include 11 subjects.