基于贝叶斯估计的广义Gamma收入分布模型

A generalized Gamma income distribution model based on Bayesian estimation

利用广义Gamma分布拟合中国西北地区(除新疆外)各省的收入分布,分布的参数使用贝叶斯方法估计,并通过Gibbs抽样得到每个参数的后验分布.估计的广义Gamma分布都通过了K-S检验.在拟合的收入分布的基础上,测算了收入不平等指数.结果表明,甘肃省和内蒙古自治区的收入不平等程度相对其他省份较严重.

The paper uses the generalized Gamma distribution to fit the income distribution of each province in the Chinese northwestern region(except Xinjiang province).The parameters of distribution are estimated using a Bayesian method and the posterior distributions of parameters are obtained by Gibbs sampling.The estimated generalized Gamma distributions have all passed the K-S test.Based on the fitted income distributions,this paper measures the income inequality indexes.The results show that income inequality in Gansu and Inner Mongolia is more serious than that in other provinces.