高值与低值空间聚类的精确检测  

Exact detection of high-value and low-value spatial clusters

作　　者：于尚洋[1] 宋向东[1] 张海森[1] 温育芳[1] 

机构地区：[1]燕山大学理学院,河北秦皇岛066004

出　　处：《燕山大学学报》2008年第1期84-86,94,共4页Journal of Yanshan University

摘　　要：提出了两个调整数据的新方法来弥补通常空间聚类检测的不足,从而能够对高值或低值聚类进行精确检测。两个方法被分别在模拟的空间类型中应用于Moran′I检测。结果表明,当不存在空间聚类时,该方法对原检测毫无影响:当有聚类趋势时,经该方法调整数据后,可以显著地检测出高值或低值聚类的存在。In this paper, two adjustment procedures are provided, which can supplement common spatial clustering tests so that one-sided conclusion can be reached. The two procedures are applied to Moran＇s Ⅰ in simulated spatial patterns respectively. The results show that the procedures have little effect on the original global testing methods when there is no clustering. When there is a clustering tendency, the procedures can unambiguously distinguish the existence of high-value clusters or low-value clusters or both.

关 键 词：空间聚类 数据调整 精确检测 

分 类 号：O212[理学—概率论与数理统计]