공간현상 분석을 위한 GIS 기반의 공간통계적 접근방법에 관한 고찰: 공간 군집지역 탐색을 위한 공간검색통계량의 실증적 사례분석 A Study on Spatial Statistical Perspective for Analyzing Spatial Phenomena in the Framework of GIS: an Empirical Example using Spatial Scan Statistic for Detecting Spatial Clusters of Breast Cancer Incidents원문보기
지리적 공간상에서 발생하는 대부분의 현상은 서로 인접한 곳에서 유사한 값을 가지는 특성이 있다. 이는 공간자기상관성과 관련이 있으며 공간분석의 존재 이유를 나타내는 개념이다. 또한 지리적 공간상에서 위치에 따라 값의 분포가 다양한 패턴을 보이게 된다. 이러한 패턴은 공간적 변이를 내포하고 있다. 즉, 특정 위치에서 항상 같은 값을 관찰할 수 있다고 단정하기는 불가능하기 때문에 이러한 변이는 본질적으로 확률론적 특성을 지닌다. 이러한 공간자료의 특성들을 무시하고 일반적 통계분석 등을 수행할 경우 공간자기상관성으로 인하여 통계분석에서 가정하는 자료 값들 간 독립성이 위배되고 분석결과는 왜곡될 가능성이 크다. 그러므로 공간자료 분석을 위해서는 공간자기상관성과 확률론적 변이를 적절하게 반영할 수 있는 수단이 필요하다. GIS는 공간적 위치정보를 처리하는데 적합하고 공간통계학은 공간적 변이를 다루는데 유용하다. 따라서 GIS를 기반으로 공간통계학을 통합하는 분석방식은 공간자료의 특성들을 고려하여 유의미한 분석을 하기에 적합한 장점이 있다. 본 연구의 목적은 공간자료 분석에 있어서 공간통계학과 GIS를 결합하는 접근방식의 유용성을 논의하고 실증적 사례분석을 통하여 구체적 활용성을 살펴보는 것이다. 이를 위하여 공간통계학을 주요 방법론으로 활용하는 공간역학(spatial epidemiology) 분야를 예시적으로 살펴보았다. 구체적으로는 공간검색통계량을 이용하여 미국 Erie 및 Niagara 카운티(New York 주) 내의 유방암 발생의 공간적 군집패턴 분석 논의하였다.
지리적 공간상에서 발생하는 대부분의 현상은 서로 인접한 곳에서 유사한 값을 가지는 특성이 있다. 이는 공간자기상관성과 관련이 있으며 공간분석의 존재 이유를 나타내는 개념이다. 또한 지리적 공간상에서 위치에 따라 값의 분포가 다양한 패턴을 보이게 된다. 이러한 패턴은 공간적 변이를 내포하고 있다. 즉, 특정 위치에서 항상 같은 값을 관찰할 수 있다고 단정하기는 불가능하기 때문에 이러한 변이는 본질적으로 확률론적 특성을 지닌다. 이러한 공간자료의 특성들을 무시하고 일반적 통계분석 등을 수행할 경우 공간자기상관성으로 인하여 통계분석에서 가정하는 자료 값들 간 독립성이 위배되고 분석결과는 왜곡될 가능성이 크다. 그러므로 공간자료 분석을 위해서는 공간자기상관성과 확률론적 변이를 적절하게 반영할 수 있는 수단이 필요하다. GIS는 공간적 위치정보를 처리하는데 적합하고 공간통계학은 공간적 변이를 다루는데 유용하다. 따라서 GIS를 기반으로 공간통계학을 통합하는 분석방식은 공간자료의 특성들을 고려하여 유의미한 분석을 하기에 적합한 장점이 있다. 본 연구의 목적은 공간자료 분석에 있어서 공간통계학과 GIS를 결합하는 접근방식의 유용성을 논의하고 실증적 사례분석을 통하여 구체적 활용성을 살펴보는 것이다. 이를 위하여 공간통계학을 주요 방법론으로 활용하는 공간역학(spatial epidemiology) 분야를 예시적으로 살펴보았다. 구체적으로는 공간검색통계량을 이용하여 미국 Erie 및 Niagara 카운티(New York 주) 내의 유방암 발생의 공간적 군집패턴 분석 논의하였다.
When analyzing geographical phenomena, two properties need to be considered. One is the spatial dependence structure and the other is a variation or an uncertainty inhibited in a geographic space. Two problems are encountered due to the properties. Firstly, spatial dependence structure, which is con...
When analyzing geographical phenomena, two properties need to be considered. One is the spatial dependence structure and the other is a variation or an uncertainty inhibited in a geographic space. Two problems are encountered due to the properties. Firstly, spatial dependence structure, which is conceptualized as spatial autocorrelation, generates heterogeneous geographic landscape in a spatial process. Secondly, generic statistics, although suitable for dealing with stochastic uncertainty, tacitly ignores location information im plicit in spatial data. GIS is a versatile tool for manipulating locational information, while spatial statistics are suitable for investigating spatial uncertainty. Therefore, integrating spatial statistics to GIS is considered as a plausible strategy for appropriately understanding geographic phenomena of interest. Geographic hot-spot analysis is a key tool for identifying abnormal locations in many domains (e.g., criminology, epidemiology, etc.) and is one of the most prominent applications by utilizing the integration strategy. The article aims at reviewing spatial statistical perspective for analyzing spatial processes in the framework of GIS by carrying out empirical analysis. Illustrated is the analysis procedure of using spatial scan statistic for detecting clusters in the framework of GIS. The empirical analysis targets for identifying spatial clusters of breast cancer incidents in Erie and Niagara counties, New York.
When analyzing geographical phenomena, two properties need to be considered. One is the spatial dependence structure and the other is a variation or an uncertainty inhibited in a geographic space. Two problems are encountered due to the properties. Firstly, spatial dependence structure, which is conceptualized as spatial autocorrelation, generates heterogeneous geographic landscape in a spatial process. Secondly, generic statistics, although suitable for dealing with stochastic uncertainty, tacitly ignores location information im plicit in spatial data. GIS is a versatile tool for manipulating locational information, while spatial statistics are suitable for investigating spatial uncertainty. Therefore, integrating spatial statistics to GIS is considered as a plausible strategy for appropriately understanding geographic phenomena of interest. Geographic hot-spot analysis is a key tool for identifying abnormal locations in many domains (e.g., criminology, epidemiology, etc.) and is one of the most prominent applications by utilizing the integration strategy. The article aims at reviewing spatial statistical perspective for analyzing spatial processes in the framework of GIS by carrying out empirical analysis. Illustrated is the analysis procedure of using spatial scan statistic for detecting clusters in the framework of GIS. The empirical analysis targets for identifying spatial clusters of breast cancer incidents in Erie and Niagara counties, New York.
* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.
문제 정의
Not that the study limitedly aims at demonstrating the spatial statistical analysis procedure integrated with GIS. Although the risk factors were not considered and adjusted in this research, dealing with those risk factors with more detailed data is necessary for more sophisticated analysis and realistic outcome in further research.
제안 방법
Based on the argument that emphasizes the utility of the third category in addressing many geographical issues, this article aims at demonstrating the procedure of utilizing spatial statistics of the third category(detection of spatial clusters) in the framework of GIS to identify local anomalies of geographic phenomena. The spatial scan statistic, among others, was chosen to illustrate the procedure for locating local hot-spots of disease incidents.
The potential and still in-debate risk factors include the exposure to environmental contaminants. Not that the study limitedly aims at demonstrating the spatial statistical analysis procedure integrated with GIS. Although the risk factors were not considered and adjusted in this research, dealing with those risk factors with more detailed data is necessary for more sophisticated analysis and realistic outcome in further research.
In the context of spatial epidemiology, cases refer to as individuals with disease while controls indicates individuals without disease in a study area. To obtain the statistic, the numbers of cases and controls falling into subregions (e.g., census tracts, zip code boundaries, etc,) that constitute a study area are marked and the likelihood ratios of alternative and null spatial patterns are calculated.
To test the statistical significance of detected clusters, the null distribution assuming no clustering with spatial randomness was simulated through 999 Monte Carlo replications, using the custom program. As a result, p-values of most clusters are 0.
후속연구
Therefore, it is extremely unlikely that the clusters of breast cancer during the study period(1997～1997) have been formed just by chance. They are all statistically significant and it is statistically plausible to say that there are a spatial process forcing the patterns to be formed and therefore, further epidemiological investigation is worth making into to find out possible causes.
참고문헌 (26)
Bailey, T.C. and A.C. Gatrell. 1995. Interactive Spatial Data Analysis, Prentice Hall, Malaysia, PA, USA. pp.24-57.
Besag, J. and J. Newell. 1991. "The detection of clusters in rare diseases", Journal of the Royal Statistical Society, Series A 154(1):143-155.
Fotheringham, A.S. and F.B. Zhan. 1996. "A comparison of three exploratory methods for cluster detection in spatial point patterns", Geographical Analysis 28(3):200-218.
Fotheringham, A.S., Brunsdon. C and M. Charlton. 2000. Quantitative Geography: Perspectives on Spatial Data Analysis, Sage Publications, London, UK. 15pp.
Fotheringham, A.S. and P.A. Rogerson. 2009. Introduction. In: A.S. Fotheringham and P.A. Rogerson.(ed.), The Sage Handbook of Spatial Analysis. Sage Publications, London, UK. 1-4pp.
Geary, R.C. 1954. "The continuity ratio and statistical mapping", The Incorporated Statistician 5(3):115-145.
Getis, A. 1999. "Spatial statistics. In: P.A. Longley et al.(ed.)", Geographic Information Systems: Principles and Technical Issues. John Willey & Sons, New York, NY, USA. 239-251pp.
Haining, R. 2009. "The special nature of spatial data. In: A.S. Fotheringham and P.A. Rogerson.(ed.)", The Sage Handbook of Spatial Analysis. Sage Publications, London, UK. pp.5-23.
Kuldorff, M. 1997. A spatial scan statistic. Communications in Statistics: Theory and Methods 26(6):1481-1496.
Kahng, B. K., I. Kweon, and T. H. Kim, 1997, An analysis methodology of spatial locational character and change of urban micro land use, with GIS & statistical analysis, in the case of Kangnam, Seoul, Journal of Geographic Information System Association of Korea, 5(1), 27-41
Kweon, I., and J. W. Kim, 2002, Urban Land Use Planning with a PSS-based Land Use Change Projection Model, Journal of Geographic Information System Association of Korea, 10(4), 515-532
Lawson, A.B. 1993. "On the analysis of mortality events associated with a prespecified fixed point", Journal of the Royal Statistical Society, Series A 156(2):363-377.
Lee, G., Yamada, A. and P.A. Rogerson. 2010. "GeoSurveillance: GIS-based exploratory spatial analysis tools for monitoring spatial patterns and clusters. In: Fisher, M. and A. Getis. (ed.)", Handbook of Applied Spatial Analysis: Software Tools, Methods and Applications. Springler, Heidelberg, Germany. pp.135-149.
Malczewski, J. 1999. GIS and Multicriteria Decision Analysis, John Wiley & Sons, New York, NY, USA. 306
Mallows, C. 1998. The zeroth problem, American Statisticians 52(1):1-9.
Moran, P.A.P. 1948. "The interpretation of statistical maps", Journal of the Royal Statistical Society, Series B 10:245-251.
Opemshaw, S., Charlton, M., Wymer, C. and A. Craft. 1987. "A mark 1 geographical analysis machine for the automated analysis for point data sets", International Journal of Geographical Information Systems 1():335-358.
Rogerson, P.A. 2005. "A set of associated statistical tests for the detection of spatial clustering", Ecological and Environmental Statistics 12(3):275-288.
Rogerson, P.A. and I. Yamada. 2009. Statistical Detection and Surveillance of Geographic Clusters, CRC Press, Boca Raton, FL, USA. 85pp.
Stone, R. 1988. "Investigation of excess environmental risks around putative sources: statistical problems and a proposed test", Statistics in Medicine 7(6):649-660.
Turnbull, B.W., Iwano, E.J., Burnett, W.S., Howe, H.L. and L.C. Clark. 1990. "Monitoring for clusters of disease: application to leukemia incidence in upstate New York", American Journal of Epidemiology 132(1):136-143.
AI-Helper
※ AI-Helper는 부적절한 답변을 할 수 있습니다.