Optimal geographic scales for local spatial statistics

Rogerson, Peter A.
April 2011
Statistical Methods in Medical Research;Apr2011, Vol. 20 Issue 2, p119
Academic Journal
Local spatial statistics are used to test for spatial association in some variable of interest, and to test for clustering around predefined locations. Such statistics require that a neighbourhood be defined around the location of interest. This is done by specifying weights for surrounding regions, and this is tantamount to specification of the scale at which the local dependence or clustering is tested. In practice, weights are usually assigned exogenously, with little thought given to their definition. Most common is the definition of binary adjacency — weights are set equal to one if the region is adjacent to the focal region and to zero otherwise. But this implies a spatial scale that may or may not be the best one to evaluate the variable under study — the actual scale of dependence or clustering is one that is smaller or larger. An alternative strategy is to try different sets of weights corresponding to different spatial scales. The purpose of this article is to provide statistical tests that allow for examination of several local statistics across multiple spatial scales, and yet avoid the need for simulation. Application of these tests leads to a choice of spatial scale through the weights, as well as an assessment of statistical significance. The approach is illustrated using data on leukemia from central New York State.


Related Articles

  • Assessing representation error in point-based coverage modeling. Murray, Alan T.; O'Kelly, Morton E. // Journal of Geographical Systems;Jun2002, Vol. 4 Issue 2, p171 

    Accurately representing geographic space in a digital environment continues to confound and challenge researchers. Carrying out spatial analysis in a setting where geographic representation is subject to change poses problems to be addressed. In this paper we examine spatial representation in...

  • Managing spatial uncertainty using attribute, geometric, and neighborhood measures in an empirical rule-based model approach. Allan, Rod; Lowell, Kim // Journal of Geographical Systems;Jun2002, Vol. 4 Issue 2, p141 

    A rule-based model for managing uncertainty in spatial databases is presented. The overall goal of the model is to allow a user to assign to a single map class each polygon whose class is not entirely certain using more information than only the map class attributes of such polygons (that are...

  • A COMPARISON BETWEEN PARAMETRIC AND NON-PARAMETRIC APPROACHES TO THE ANALYSIS OF REPLICATED... Diggle, Peter J.; Mateu, Jorge // Advances in Applied Probability;Jun2000, Vol. 32 Issue 2, p331 

    Compares non-parametric, or design-based, or parametric, or model-based, approaches to the analysis of data in the form of replicated spatial point patterns in two or more experimental groups. Summary of the reduced second moment measure by the non-parametric approach; Use of model parameter...

  • Incorporating Space into Fisheries Models: Comment.  // American Journal of Agricultural Economics;Nov2000, Vol. 82 Issue 5, p1210 

    Comments on the integration of spatial analysis in econometric models of fisheries. Advantages of the application of spatial analysis on fisheries location; Impact of the spatial closure orders in Hawaii to protect sea turtles; Methodological issues associated with the analysis of the spatial...

  • VORONOI AND FRACTAL COMPLEX NETWORKS AND THEIR CHARACTERIZATION. Da Fontoura Costa, Luciano // International Journal of Modern Physics C: Computational Physics;Jan2004, Vol. 15 Issue 1, p175 

    Real world networks are often characterized by spatial constraints such as the relative position and adjacency of nodes. The present work describes how Voronoi tessellations of the space where the network is embedded provide not only a natural means for relating such networks with metric spaces,...

  • An Empirical Evaluation of Alternative Spatial Models of Elections. Enelow, James M.; Hinich, Melvin J.; Mendell, Nancy R. // Journal of Politics;Aug86, Vol. 48 Issue 3, p675 

    Presents an empirical evaluation of two alternative spatial models of elections. Extension of the spatial theory of elections by James Enelow and Melvin Hinich to incorporate non-spatial characteristics in the voter's candidate evaluations; Introduction of an interactive voting model by Bernard...

  • A Method for Improved Analyses of Scalars and Their Derivatives. Spencer, Phillip L.; Stensrud, David J.; Fritsch, J.Michael // Monthly Weather Review;Nov2003, Vol. 131 Issue 11, p2555 

    Analytic observations are used to compare the traditional and triangle methods for the objective analysis of scalar variables. The traditional method for objective analysis assigns gridpoint values based on the distance from the grid points to each member of the set of observations....

  • Kriging and Bilinear Methods for Estimating Spatial Pattern of Atmospheric Pollutants. Carletti, Roberto; Picci, Maria; Romano, Daniela // Environmental Monitoring & Assessment;Jul2000, Vol. 63 Issue 2, p341 

    Two statistical methods to reconstruct the spatial pattern of environmental data are compared: the Kriging and the Bilinear. The comparison is performed by evaluating two different characteristics of the methods: the interpolation and the estimation. The Kriging method is demonstrated to be...

  • Test Development Study On The Spatial Visualization. YÜKSEL, Nazan SEZEN; BÜLBÜL, Ali // Necatibey Faculty of Education Electronic Journal of Science & M;2014, Vol. 8 Issue 2, p124 

    Spatial visualization, frequently used in many stages of daily life, is also an indispensable part of mathematics and geometry courses. There are many definitions of spatial visualization ability and various tests have been developed to measure this ability. The aim of this study is to develop a...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics