地理加權迴歸在視覺化分析之探討

Using Geographically Weighted Regression for Spatial Data Visualization

余清祥(Jack C. Yue)；梁穎誼(Yin-Yee Leong)；郭柔芸(Rou-Yun Kuo)

地理加權迴歸 ； 空間統計 ； 視覺化 ； 探索性資料分析 ； 電腦模擬 ； Geographically Weighted Regression ； Spatial Statistics ； Data Visualization ； Exploratory Data Analysis ； Simulation

中國統計學報

60卷4期（2022 / 12 / 01）

208 - 232

繁體中文

近年大數據蓬勃發展，統計分析的應用更為廣泛，各領域資料以不同型態出現，資料視覺化（Data Visualization）成為探索性資料分析（Exploratory Data Analysis）的核心。視覺化對於空間資料尤為重要，藉由圖表等工具可有效地呈現資料主要特性，包括空間異質性（Spatial Inhomogeneity）、空間自相關（Spatial Autocorrelation），做為後續研究進行的依據。地理加權迴歸（GWR，Geographically Weighted Regression）可視為空間資料的迴歸分析，描述目標變數與解釋變數間的局部關係，用於展示變數關係隨地理位置的變化。本文探討地理加權迴歸的適用時機，透過電腦模擬說明GWR的限制及可能問題，測試修正方法是否有效，同時提出這個方法的使用建議。

Data appear in many different forms in the age of big data, and applications of data analysis have become more extensive recently. Data Visualization is the core of Exploratory Data Analysis, which is particularly important for the analysis of spatial data. Visualization tools, such as graphs and tables, can effectively present the main characteristics of the data, including spatial homogeneity and spatial autocorrelation. Geographically Weighted Regression (GWR) describes the local relationship between target variables and explanatory variables, and is used to show the change of variable relationship with geographic locations. This paper discusses the applicable timing of GWR, illustrates the limitations and possible problems of GWR through computer simulation, and tests whether the modification of GWR is effective.

1. 李宗儒,陳昭榮,李妙純(2021)。臺灣大腸癌死亡率之空間分析。臺灣衛誌，40(2)，225-240。
   連結：
2. Brunsdon, C.,Fotheringham, A. S.,Charlton, M. E.(1998).Geographically Weighted Regression-Modelling Spatial Non-stationarity.Statistician,47(3),431-443.
3. Brunsdon, C.,Fotheringham, A. S.,Charlton, M. E.(1996).Geographically Weighted Regression: A Method for Exploring Spatial Nonstationarity.Geographical analysis,28(4),281-298.
4. Chan, T.,Chiang, P.,Su, M.,Wang, H.,Liu, M. S.(2014).Geographic Disparity in Chronic Obstructive Pulmonary Disease (COPD) Mortality Rates among the Taiwan Population.PLOS ONE,9(5),e98170.
5. Edayu, Z. N.,Syerrina, Z.(2018).A statistical analysis for geographical weighted regression.The 9th IGRSM International Conference and Exhibition on Geospatial & Remote Sensing,Malaysia:
6. Fotheringham, A. S.,Brunsdon, C.,Charlton, M. E.(2002).Geographically Weighted Regression: The Analysis of Spatially Varying Relationships.John Wiley & Sons.
7. Fotheringham, A.S.,Yang, W.,Kang, W.(2017).Multiscale Geographically Weighted Regression (MGWR).Annals of the American Association of Geographers,107(6),1247-1265.
8. Leong, Y.,Yue, C. J.(2017).A Modification to Geographically Weighted Regression.International Journal of Health Geographics,16(1)
9. Matthews, S. A.,Yang, T-C.(2012).Mapping the Results of Local Statistics: Using geographically Weighted Regression.Demographic Research,26,151-166.
10. Silverman, B. W.(1985).Spline Aspects of Spline Smoothing Approaches to Nonparametric Regression Curve Fitting.Journal of the Royal Statistical Society, Series B,47(1),1-52.
11. Tobler, W.(1970).A Computer Movie Simulating Urban Growth in the Detroit Region.Economic Geography,46,234-240.
12. Tukey, J. W.(1977).Exploratory Data Analysis.Reading, Mass:Addison-Wesley Pub. Co..
13. Wheeler, D. C.(2010).Visualizing and Diagnosing Coefficients from Geographically Weighted Regression Models.Geospatial Analysis and Modelling of Urban Structure and Dynamics,Dordrecht:
14. Yu, H.,Fotheringham, A. S.,Li, Z.,Oshan, T.,Kang, W.,Wolf, L. J.(2020).Inference in Multiscale Geographically Weighted Regression.Geographical Analysis,52(1),87-106.
15. 凃明蕙(2020)。國立政治大學商學院統計學系。

1. 梁穎誼,梁舒涵,余清祥(2023)。空間異質性檢測方法之比較及其在臺灣主要死因的應用。人口學刊，66，1-40。