Bayesian nearest-neighbor analysis via record value statistics and nonhomogeneous spatial Poisson processes

被引:9
|
作者
Yang, Tae Young [1 ]
Lee, Jae Chang
机构
[1] Myongji Univ, Dept Math, Yongin 449728, South Korea
[2] Korea Univ, Dept Stat, Seoul 136701, South Korea
关键词
nearest-neighbor approaches; nonhomogeneous spatial Poisson processes; record value statistics;
D O I
10.1016/j.csda.2006.07.001
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
This article proposes record value statistics and nonhomogeneous spatial Poisson processes as new nearest-neighbor approaches for detecting spatial patterns. A Markov chain Monte Carlo method with data augmentation was developed to compute the Bayes estimates of posterior quantities of interest. Simulation studies showed that the new approaches yield high detection rates and low false positive rates. We applied the new approaches to detect localized clusters of specific trees and to outline seismic faults in the study space. (c) 2006 Elsevier B.V. All rights reserved.
引用
收藏
页码:4438 / 4449
页数:12
相关论文
共 26 条