聚类分析在我国城镇居民消费结构研究中的应用

Application of Clustering Analysis to Research Consumption Structure of Households in Chinese Suburb Area

选用了8个聚类分析统计指标用离差平方和法,对各地区城镇居民消费结构相似程度进行了聚类分析,不仅从总体上掌握了消费结构类型的地区分布,而且系统阐述了各地区消费结构的特点及产生原因,同时提出用恩格尔系数来衡量生活水平高低的局限性,得出在确定地区生活水平评价体系时应加入非食品性支出构成的使用力度的结论.

In this paper, eight statistics indexes of clustering analysis are chosen regarding consumptive structure of households in Chinese suburb area. Clustering analysis is applied in consumption structure similarity degree of households by means of deviation squared summation. Not only we master the region distribution of consumptive structure type generally, but also introduce the character and reason of each type. At the same time we point out the limitation of Engel coefficient to measure the level of living. We draw a conclusion that we should strengthen the use of non - food expenditure composition when we determine judgement index system of region level of living.