The Application Of Clustering Analysis Based On SPSS In Industry Statistical Data

Since the reform and opening up, every industry has got a leap in progress with the rapiddevelopment of China’s rapid economic. Technology and science play an important role ineconomic development. People have reached a comfortable level in general, and China hasbecome one of the most potential countries in the world. The economy of China is inseparablefrom the reform of China’s development and technology. The economy is also inseparablefrom all walks of life to work hard.China has successively completed some five-year plans in these fifty years since the yearof1850. China’s achievements are obvious to all around the world in the fifty years, andChina’s economy has grown fast, and laid a very solid foundation for the development of thenational economy.The object of this paper is the China Statistical Yearbook-2012’s industry statistics. Thedata contains the year’s industry statistics and region’s industry statistics. The main modelestablished in this paper is the Principal Component Analysis-Clustering model. The mainidea of Principal Component Analysis-Clustering model is using the idea of PrincipalComponent Analysis to Clustering. Firstly, we make Principal Component Analysis for thedata, and then we get the principal component of the data, at last, we make clustering for theprincipal component.Two models are going to be established in this paper. The first model is to makePrincipal Component Clustering for the data of year’s industry data; and the second model isto make Principal Component Clustering for the data of region’s industry data.For the first model, specific steps are as follows:(1) Make pre-processing for China Statistical Yearbook-2012’s year’s industry statisticsdata.(2) Make Principal Component Analysis for the year’s industry data.(3) Make Clustering Analysis for the principal component, and we can get the result ofclustering for years. For the second model, specific steps are as follows:(1) Make pre-processing for China Statistical Yearbook-2012’s region’s industrystatistics data.(2) Make Principal Component Analysis for the region’s industry data.(3) Make Clustering Analysis for the principal component, and we can get the result ofclustering for regions.With these two models above, we can make a better understanding of China’s economicinformation.