The Kernel Density Estimation of China's City-size Distribution and Dynamic Evolution Analysis

摘要

Traditional studies about the distribution of city size, often a priori assumption that the distribution is the Pareto distribution of city size, but in fact merely a special case of Pareto distribution. In estimating the parameters of the distribution of city size, you should use some statistical methods to test whether the establishment of Pareto distribution. In this paper, non-parametric statistical methodskernel density estimation the distribution of city size in China is analyzed. And this regression model using panel data methods to solve the traditional rank-size laws omitted variable regression equation problem. From the estimates show that from 1994-1998 China's city-size distribution of the Pareto index revealed a growth, then decreased, and then rising. This reflects the characteristics of China's current urban growth. Rapid urbanization process, making the role of the city's rapidly increasing concentration.