"时空接近"空间自相关模型构建及其应用——以长三角区域经济差异分析为例
收稿日期: 2009-01-18
修回日期: 2009-06-10
网络出版日期: 2010-02-20
基金资助
国家自然科学基金项目(40871070);中国科学院知识创新工程重要方向项目(KZCX2-YW-321)
Construction of spatial autocorrelation method of spatial-temporal proximity and its application: Taking regional economic disparity in the Yangtze River Delta as a case study
Received date: 2009-01-18
Revised date: 2009-06-10
Online published: 2010-02-20
地理学第一定律是空间自相关统计学的核心和基石,传统的空间自相关以邻接性或空间距离函数确定空间权重矩阵。但随着快速交通网络变得具有渗透性,空间距离内涵已发生质的变化,"接近"概念有必要从"空间接近"拓展为"时空接近"。基于这一新的内涵,提出"时空接近"空间自相关概念并构建相应计算模型,结合表征时间距离的可达性指标将该模型应用于长三角区域经济差异分析。通过计算全局Moran's I和局域Moran's I,结果表明:在全局空间自相关指标上,"时空接近"空间自相关能更好地揭示地理事物间的关联动态变化。在局域空间自相关指标上,当时间距离截取在合理范围时,邻接性表现出较强的稳健性,但"时空接近"与传统"空间接近"的空间相关性存在较大差异,两者结合能更客观揭示地理事物空间关联的现象和本质。
关键词： "时空接近"空间自相关; 空间权重矩阵; 可达性; 区域经济差异; 长三角
吕韬,曹有挥 . "时空接近"空间自相关模型构建及其应用——以长三角区域经济差异分析为例[J]. 地理研究, 2010 , 29(2) : 351 -360 . DOI: 10.11821/yj2010020017
Tobler's First Law is the core and the basis of spatial autocorrelation statistics. Spatial weight matrix is decided by the traditional spatial autocorrelation in the way of proximity or the given distance function. The rapid transportation networks are becoming saturated; hence, the meaning of spatial distance changes essentially. The connotation of proximity should be extended from "spatial proximity" to "spatial-temporal proximity". Based on such connotation, we propose a new concept-spatial autocorrelation of spatial-temporal proximity, and construct the corresponding calculation method. This study applies the above concept and method to regional economic disparity in the Yangtze River Delta, focusing on the index of accessibility. By examining the indexes of Global Moran's I and Local Moran's I, we have the following findings: (1) In terms of GISA, spatial autocorrelation of spatial-temporal proximity is a better approach to the dynamic change of relations between different geographic units than the traditional spatial autocorrelation. (2) For LISA, proximity has better robustness when temporal distance is in a reasonable range. (3) However, there are differences in spatial autocorrelation between spatial-temporal proximity and space proximity to a certain extent. So the combination of the above-mentioned two concepts is helpful to reveal the laws behind the dynamics of spatial relationship among geographic units.
Key words： spatial autocorrelation of spatial-temporal proximity; spatial weight matrix; accessibility; regional economic disparity; Yangtze River DeltaKey words: spatial autocorrelation of spatial-temporal proximity; spatial weight matrix; accessibility; regional economic disparity; Yangtze River Delta
[1] Harvey J M.Tobler's First Law and spatial analysis.Annals of the Association of American Geographers, 2004,94(2):284~289.
[2] Cliff A D,Ord J K.Testing for spatial autocorrelation among regression residuals. Geographical Analysis,1972,4:267~284.
[3] Geary R C.The contiguity ratio and statistical mapping.The Incorporated Statistician, 1954,5(3):115~145.
[4] Goodchild M F. Spatial Autocorrelation.CATMOG(Norwich,UK: GeoBooks),1986.6~25.
[5] Dubin R.Spatial autocorrelation and neighborhood quality.Regional Science and Urban Economics,1992,22:433~452.
[6] 李天生,周国法.空间自相关与分布型指数研究.生态学报,1994,14(3):327~331.
[7] Aten B. Evidence of spatial autocorrelation in international prices.Review of Income and Wealth,1996,42:149~63.
[8] 张朝生,章申,何建邦.长江水系沉积物重金属含量空间分布特征研究——空间自相关与分形方法. 地理学报,1998,53(1):87~96.
[9] Basu S,Thibodeau T G.Analysis of spatial autocorrelation in housing prices.The Journal of Real Estate Finance and Economics,1998, 17:61~85.
[10] Ord J K,Getis A. Testing for local spatial autocorrelation in the presence of global autocorrelation.Journal of Regional Science, 2001, 41: 411~432.
[11] 孟斌,张景秋,王劲峰,等. 空间分析方法在房地产市场研究中的应用——以北京市为例.地理研究,2005,24(6):956~965.
[12] LIU Jisheng,CHEN Yanguang.Spatial autocorrelation and localization of urban development. Chinese Geographical Science,2007,17(1):34~39.
[13] 马荣华,顾朝林,蒲英霞,等.苏南沿江城镇扩展的空间模式及其测度.地理学报,2007,62(10):1011~1022.
[14] Moran P.The interpretation of statistical maps.Journal of the Royal Statistical Society,1948,10:243~251.
[15] Getis A,Ord J K.The analysis of spatial association by the use of distance statistics.Geographical Analysis,1992,24(3):189~206.
[16] Anselin L.Local indicators of spatial association—LISA.Geographical Analysis,1995,27(2):93~115.
[17] Tobler W A.A computer movie simulating urban growth in the Detroit region.Economic Geography,1970,46(2):234~240.
[18] James P L.The Theory and Practice of Spatial Econometrics.Toledo,1999.11~14.
[19] 刘仲刚,李满春,刘剑锋,等.面向离散点的空间权重矩阵生成算法与实证研究.地理与地理信息科学,2006,22(3):53~56.
[20] 何彬彬,郭达志,方涛.基于空间统计学的空间关联挖掘.计算机工程,2006,32(5):20~22.
[21] 陈炳为,许碧云,倪宗瓒,等.地理权重回归模型在甲状腺肿大中的应用.数理统计与管理,2005,24(3):113~117.
[22] Casti J L.Searching for Certainty: What Scientists Can Know about the Future. William Morrow,New York,1990.
[23] Swartz N.Laws of nature.The Internet dictionary of philosophy. 2001. http://www.utm.edu /research/iep/
[24] 柴彦威.城市空间.北京:科学出版社,2000.
[25] 石崧, 宁越敏.人文地理学"空间"内涵的演进.地理科学,2005,25(3):340~345.
[26] Anselin L.Spatial econometrics.Baltagi B(ed.).Companion to Econometrics.Oxford: Basil Blackwell,2000.
[27] Cliff A D, Ord J K.Spatial Processes:Models and Applications.London:Pion,1981.
[28] 沈绿珠.空间关联分析及其应用.统计与决策,2006,(8):28~30.
[29] 陆大道,薛凤旋,金凤君.1997中国区域发展报告.北京:商务印书馆,1998.16~26.
[30] 王绍光,胡鞍钢.中国:不平衡的政治经济学.北京:中国计划出版社,1999.46~50.
[31] 蒲英霞,葛莹,等.基于ESDA的区域经济空间差异分析——以江苏省为例.地理研究,2005,24(6):965~974.
/
| 〈 |
|
〉 |