The purpose of this article was to introduce the basic concepts, calculation methods, two examples and the implementation of SAS calculation methods related to cluster analysis of disordered samples. The basic concepts included disordered samples and ordered samples, cluster analysis and comprehensive evaluation, high superiority indicators, low superiority indicators and expected indicators, sorting and grading, and standardized transformation. The calculation method involved the comprehensive scoring methods calculation formula based on expert ratings and the comprehensive scoring methods calculation formula based on variable observations. The data in the two examples were "survey data on the expenditure of farmers in 16 regions of China in 1982" and "detection results of ion concentration and pH value concentration in precipitation in 17 regions of China during a certain period of time in a certain year". Using SAS software, cluster analysis of disordered samples was performed on the data from two instances, furthermore, the graded results were provided, along with an explanation of the SAS output results. |