Econometrics Studying On Consumption Composition Of Chinese Urban Households

Consumption composition is an important part of economic composition, reflects the consumption contents, and the consumption levels and consumption quality, and the consumption situation. Therefore, to study the Consumption composition is of significance both in theory and in practice.The theme of this dissertation is to study the evolvement of consumption composition of Chinese urban households, and to discuss the impact of a few factors, such as region difference and income distribution, on consumption composition by employing the econometrics models. Then based on the experimental conclusions, the author presents some suggestions for the Chinese macroeconomic policy-making.The article includes four parts:Chapter one: the author introduces what's consumption and what's consumption composition. And explains why he chooses this topic and summarizes research fruits of predecessors at home and abroad. Based on the above mentioned facts, the author draws the fundamental trails of thoughts and main contents.Chapter two: In this part, the author studies the evolvement of consumption composition of Chinese urban households by Descriptive statistics.Chapter three: In this part, the author utilizes the Factor Analysis to discuss the effect of region difference, and utilizes the Panel Data Model to discuss the impact of income distribution on consumption composition.Chapter four: To summarize the conclusions that mentioned in the previous chapter, and to offer some suggestions.The major contributions of this dissertation are that:1. In the study of the effect of region difference, the author poses that the Factor Analysis can analyze area effects on consumption composition. Factor analysis is a statistical technique used to reduce a set of variables to a smaller number of variablesor factors. China is a large country, the regional economic doesn't develop evenly. Factor analysis examines the pattern of intercorrelations between the regions, and determines whether there are subsets of variables (or factors) that correlate highly with each other but that show low correlations with other subsets (or factors).2. In the study of the impact of income distribution on consumption composition, the author poses that the Panel Data Model can analyze it. Panel Data are data where multiple cases (people, firms, countries etc) were observed at two or more time periods. There are two kinds of information in cross-sectional time-series data: the cross-sectional information reflected in the differences between subjects, and the time-series or within-subject information reflected in the changes within subjects over time. Panel data regression techniques allow you to take advantage of these different types of information. Because of the inconsistency of family survey data, to use the Panel Data Model can increase the sample capacity and reduce the estimated bias when analyzing the information.