A Permutation Test for Identifying Significant Clusters in Spatial Dataset
TANG Jianbo, Qiliang Liu, DENG Min, Jincai Huang, Jiannan Cai · DOAJ (DOAJ: Directory of Open Access Journals) · 2016
Spatial hierarchical clustering methods considering both spatial proximity and attribute similarity play an important role in exploratory spatial data analysis. Although existing methods are able to detect multi-scale homogeneous spatial contiguous clusters, the significance of these clusters cannot be evaluated in an objective way. In this study, a permutation test was developed to determine the significance of clusters discovered by spatial hierarchical clustering methods. Experiments on both simulated and meteorological datasets show that the proposed permutation test is effective for determining significant clustering structures from spatial datasets.