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

Authors:
Tae Young Yang;Jae Chang Lee
Affiliations:
Department of Mathematics, Myongji University, Yongin 449-728, South Korea;Department of Statistics, Korea University, 5-1 Anam-dong, Sungbuk-ku, Seoul 136-701, South Korea
Venue:
Computational Statistics & Data Analysis
Year:
2007

Citing 2
Cited 2

Finding Curvilinear Features in Spatial Point Patterns: Principal Curve Clustering with Noise

IEEE Transactions on Pattern Analysis and Machine Intelligence
A logarithmic poisson execution time model for software reliability measurement

ICSE '84 Proceedings of the 7th international conference on Software engineering

Efficient multi-class cancer diagnosis algorithm, using a global similarity pattern

Computational Statistics & Data Analysis
Multi-scale decomposition of point process data

Geoinformatica

Quantified Score

Hi-index	0.03

Visualization

Abstract

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.