基于异窗宽GTWR模型的商品住宅价格影响因素研究  

Research on Influencing Factors of House Prices Based on Multi-Bandwidth GWTR Model

作　　者：侯健[1,2,3] 王芝皓 田茂再 窦燕[3] HOU Jian;WANG Zhi-hao;TIAN Mao-zai;DOU Yan(Center for Applied Statistics,Renmin University of China,Beijing 100872,China;School of Statistics,Renmin University of China,Beijing 1008721,China;School of Statistics and Data Science,Xinjiang University of Finance,Urumqi 830012,China)

机构地区：[1]中国人民大学应用统计中心,北京100872 [2]中国人民大学统计学院,北京100872 [3]新疆财经大学统计与数据科学学院,新疆乌鲁木齐830012

出　　处：《数理统计与管理》2022年第6期1003-1014,共12页Journal of Applied Statistics and Management

基　　金：中国人民大学科学研究基金(中央高校基本科研业务费专项资金资助)(22XNL016)。

摘　　要：随着数据可获得性的增强,时空数据被广泛地应用在各个领域。以中国西部干旱区代表城市乌鲁木齐为研究对象,本文根据标准差椭圆加权算法与时空地理加权回归模型(GTWR)提出异窗宽GTWR模型对房屋价格变动影响因素的时空变化进行研究。结果表明乌鲁木齐市住房价格的变动存在着明显的空间异质性,异窗宽GTWR模型对其的解释能力较好,标准差椭圆加权算法有效的减少了计算量,房价变动在空间上受交通便利性和绿化率等因素的影响较大,时间上受建筑年龄因素影响较大。With the increasing availability of data,spatiotemporal data is widely used in various fields.Taking Urumqi,a representative city in the arid region of western China as the research object,in this paper,the Multi-Bandwidth GWTR model is proposed to study the space and time changes of factors affecting house price changes based on the standard deviation elliptic weighting algorithm and the geographical and temporal weighted regression(GTWR).The results are showed that there is obvious spatial heterogeneity in the changes of urban house prices in the western arid area.A better interpretation performance has been represented by the Multi-Bandwidth GWTR mode.The standard deviation ellipse weighting algorithm effectively reduces the calculation amount,and the housing price changes in space It is greatly influenced by factors such as transportation convenience and greening rate,and time is greatly influenced by building age.

关 键 词：时空数据 干旱区商品住宅 空间异质性 标准差椭圆算法 异窗宽时空地理加权回归模型 

分 类 号：F293.3[经济管理—国民经济] F224[理学—概率论与数理统计] O212[理学—数学]