UWA logo
UWA logo
Skip Navigation Links
Publication Details
Output Category: C1
Strategic Research Area: None
TISI Citations: 1 PlumX StatisticsPlumX Statistics
Scopus Citations:
Journal Impact: 0.91
All Authors: McSwiggan, G, Baddeley, A, Nair, G Number:
UWA Authors: McSwiggan, G., Baddeley, A., Nair, G. Number: 3
Title: Kernel Density Estimation on a Linear Network
ISBN/ISSN 0303-6898
Year: 2016
Pages: 324-345
Volume: 44
Full Reference (Harvard Style): McSwiggan, G., Baddeley, A., Nair, G. 2016, 'Kernel Density Estimation on a Linear Network', SCANDINAVIAN JOURNAL OF STATISTICS, 44, pp. 324-345.
This paper develops a statistically principled approach to kernel density estimationon a network of lines, such as a road network. Existing heuristic techniques are reviewed, andtheir weaknesses are identi?ed. The correct analogue of the Gaussian kernel is the ‘heat kernel’,the occupation density of Brownian motion on the network. The corresponding kernel estimatorsatis?es the classical time-dependent heat equation on the network. This ‘diffusion estimator’ hasgood statistical properties that follow from the heat equation. It is mathematically similar to anexisting heuristic technique, in that both can be expressed as sums over paths in the network. How-ever, the diffusion estimate is an in?nite sum, which cannot be evaluated using existing algorithms.Instead, the diffusion estimate can be computed rapidly by numerically solving the time-dependentheat equation on the network. This also enables bandwidth selection using cross-validation. Thediffusion estimate with automatically selected bandwidth is demonstrated on road accident data.