基于稳健主成分估计的建城区面积变化驱动力分析——以重庆市为例  

Driving Force Analysis of Urban Built-up Area Change Based on Robust Principal Component Estimation——Taking Chongqing City as an Example

作　　者：张亚利[1,2] 唐菲菲[1,2] ZHANG Ya-li TANG Fei-fei(School of Civil Engineering, Chongqing University, Chongqing 400045, China Key Laboratory of New Technology for Construction of Cities in Mountain Area of Ministry of Education, Chongqing University, Chongqing 400045, China)

机构地区：[1]重庆大学土木工程学院,重庆400045 [2]重庆大学山地城镇建设与新技术教育部重点实验室,重庆400045

出　　处：《西南大学学报（自然科学版）》2017年第2期107-113,共7页Journal of Southwest University(Natural Science Edition)

基　　金：国家"十二五"科技支撑计划(2012BAJ22B00);国家自然科学基金项目(41401380)

摘　　要：建成区面积变化的驱动力分析是近年来土地利用领域的研究热点.针对动力系统多重共线性及样本粗差问题,将主成分估计和稳健估计有机结合,构成稳健主成分估计,并以重庆市建成区面积变化的驱动分析为例,对稳健主成分估计方法的有效性进行了验证与分析.研究表明:当样本含有粗差时,稳健主成分方法得出的驱动规律更科学、客观,说明稳健主成分方法系统性更强,对粗差有一定的抑制作用.Driving force analysis of urban built-up area change has become a primary type of land use change.According to multicollinearity of driving forces and block errors of samples,robust principal component estimation is established based on principal component estimation and robust estimation.Taking urban built-up area change of Chongqing city as an example,validity of robust principal component estimation is checked and analyzed.The results show that,as some block errors are in samples,the rule derived from robust principal component estimation is more scientific and objective,so robust principal component estimation is more systematic and brings down the influence of block errors.

关 键 词：主成分 驱动力 稳健估计 重庆市 

分 类 号：F301[经济管理—产业经济]