Efficient Code for Second Order Analysis of Events on a Linear Network

Suman Rakshit, Adrian Baddeley, Gopalan Nair

Research output: Contribution to journalArticle

Abstract

We describe efficient algorithms and open-source code for the second-order statistical analysis of point events on a linear network. Typical summary statistics are adaptations of Ripley's K-function and the pair correlation function to the case of a linear network, with distance measured by the shortest path in the network. Simple implementations consume substantial time and memory. For an efficient implementation, the data structure representing the network must be economical in its use of memory, but must also enable rapid searches to be made. We have developed such an efficient implementation in C with an R interface written as an extension to the R package spatstat. The algorithms handle realistic large networks, as we demonstrate using a database of all road accidents recorded in Western Australia.

Original languageEnglish
Pages (from-to)1-37
Number of pages37
JournalJournal of Statistical Software
Volume90
Issue number1
DOIs
Publication statusPublished - Jul 2019

Cite this

@article{2d1d7e779b964a0ebc6920cb66791d10,
title = "Efficient Code for Second Order Analysis of Events on a Linear Network",
abstract = "We describe efficient algorithms and open-source code for the second-order statistical analysis of point events on a linear network. Typical summary statistics are adaptations of Ripley's K-function and the pair correlation function to the case of a linear network, with distance measured by the shortest path in the network. Simple implementations consume substantial time and memory. For an efficient implementation, the data structure representing the network must be economical in its use of memory, but must also enable rapid searches to be made. We have developed such an efficient implementation in C with an R interface written as an extension to the R package spatstat. The algorithms handle realistic large networks, as we demonstrate using a database of all road accidents recorded in Western Australia.",
keywords = "geometric correction, K-function, pair correlation function, point process, R, shortest-path distance, spatstat",
author = "Suman Rakshit and Adrian Baddeley and Gopalan Nair",
year = "2019",
month = "7",
doi = "10.18637/jss.v090.i01",
language = "English",
volume = "90",
pages = "1--37",
journal = "Journal of Statistical Software",
issn = "1548-7660",
publisher = "University of California at Los Angeles",
number = "1",

}

Efficient Code for Second Order Analysis of Events on a Linear Network. / Rakshit, Suman; Baddeley, Adrian; Nair, Gopalan.

In: Journal of Statistical Software, Vol. 90, No. 1, 07.2019, p. 1-37.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Efficient Code for Second Order Analysis of Events on a Linear Network

AU - Rakshit, Suman

AU - Baddeley, Adrian

AU - Nair, Gopalan

PY - 2019/7

Y1 - 2019/7

N2 - We describe efficient algorithms and open-source code for the second-order statistical analysis of point events on a linear network. Typical summary statistics are adaptations of Ripley's K-function and the pair correlation function to the case of a linear network, with distance measured by the shortest path in the network. Simple implementations consume substantial time and memory. For an efficient implementation, the data structure representing the network must be economical in its use of memory, but must also enable rapid searches to be made. We have developed such an efficient implementation in C with an R interface written as an extension to the R package spatstat. The algorithms handle realistic large networks, as we demonstrate using a database of all road accidents recorded in Western Australia.

AB - We describe efficient algorithms and open-source code for the second-order statistical analysis of point events on a linear network. Typical summary statistics are adaptations of Ripley's K-function and the pair correlation function to the case of a linear network, with distance measured by the shortest path in the network. Simple implementations consume substantial time and memory. For an efficient implementation, the data structure representing the network must be economical in its use of memory, but must also enable rapid searches to be made. We have developed such an efficient implementation in C with an R interface written as an extension to the R package spatstat. The algorithms handle realistic large networks, as we demonstrate using a database of all road accidents recorded in Western Australia.

KW - geometric correction

KW - K-function

KW - pair correlation function

KW - point process

KW - R

KW - shortest-path distance

KW - spatstat

U2 - 10.18637/jss.v090.i01

DO - 10.18637/jss.v090.i01

M3 - Article

VL - 90

SP - 1

EP - 37

JO - Journal of Statistical Software

JF - Journal of Statistical Software

SN - 1548-7660

IS - 1

ER -