A test for spatial randomness based on k-NN distances

Authors:
Guangzhou Zeng;Richard C Dubes
Affiliations:
Department of Computer Science, Michigan State University, East Lansing, MI 48824, USA;Department of Computer Science, Michigan State University, East Lansing, MI 48824, USA
Venue:
Pattern Recognition Letters
Year:
1985

Citing 3
Cited 1

An Algorithm for Finding Nearest Neighbors

IEEE Transactions on Computers
Testing for Uniformity in Multidimensional Data

IEEE Transactions on Pattern Analysis and Machine Intelligence
A test of randomness based on the minimal spanning tree

Pattern Recognition Letters

Loevinger's measures of rule quality for assessing cluster stability

Computational Statistics & Data Analysis

Quantified Score

Hi-index	0.10

Visualization

Abstract

This paper examines a new statistic based on k-NN distances for assessing the uniformity of a set of points in a d-dimensional space and proposes the growing frame method for dealing with unknown sampling windows. The proposed statistic is evaluated in three Monte Carlo experiments and applied to the Iris Data.