江苏县域经济要素关系及演化过程的分位数回归  

Study on Economic Factor Relation of Jiangsu Counties and Evolution Process Based on Quantile Regression

作　　者：柯文前[1] 陆玉麒[1] 俞肇元[1] 陈伟[2] 王晗[1] 

机构地区：[1]南京师范大学地理科学学院,江苏南京210023 [2]东北师范大学地理科学学院,吉林长春130024

出　　处：《地理与地理信息科学》2013年第5期72-77,F0002,共7页Geography and Geo-Information Science

基　　金：国家自然科学基金项目(41071084);江苏省研究生科研创新计划项目(CXZZ13_0398)

摘　　要：针对经典回归模型的"两难问题",引入非参数的分位数回归构建了要素关系模型,并以江苏县域经济为案例分析。结果表明:1)相比OLS回归,分位数回归对县域经济总体模拟效果和刻画演化特征能力更优;2)根据变量关系结构,将县域经济发展驱动机制划分为产业结构占优型、一般均衡驱动型和高效均衡驱动型;3)苏锡常各县市受因子波动影响而使得驱动机制发生改变导致演化过程的分位点跃迁,表现出发展路径选择具有多样化的特点。For the problems which the assumption of strong conditions in using OLS to estimate parameters in regression models and ＂dilemma＂ in series testing, This paper introduces the nonparametric quantile regression to construct elements relationship models, and takes a case of Jiangsu counties economic development during 2000-2010 to analysis. The results show that; 1） Compared with OLS, QR fitting results for the counties economics overall simulation effects and the abilities of describing evo- lution character is better. 2）According to the variables relationship structure of QR,we can divide the driving mechanisms into three different types：industrial structure dominant,general equilibrium driving and efficient equilibrium driving. 3）The regions have structural changes in evolution process in Suzhou-Wuxi-Changzhou, the quantile points of every countyrs evolution process transition affected by the economic factors waved during the periods and driving mechanism changed, and the counties develo- ping path shows diversification.

关 键 词：分位数回归 经济要素关系 演化过程 区域经济 苏锡常 

分 类 号：F127[经济管理—世界经济]