Non-stationary Covariance Functions for Spatial Data on Linear Networks
We introduce a novel class of non-stationary covariance functions for random fields on linear networks that allows both the variance and the correlation range of the random field to vary spatially.The proposed covariance functions are useful to model random fields with a spatial dependence that is locally isotropic with respect to the resistance metric, a distance that reflects the topology of the network.We assess the statistical and computational performance of a weighted local likelihood estimator for the proposed models using synthetic data generated on the street network of the University of Chicago neighborhood.The framework also admits explicit stochastic representations of the associated random fields, as well as an extension to matrix-valued covariance functions for vector-valued random fields.
Authors
- Alfredo Alegría (ORCID: https://orcid.org/0000-0001-9720-7697)
Institutions
- Pontificia Universidad Católica de Chile (CL)
Publication Details
- Journal
- Statistica Sinica
- Published
- 2026-11-18
- DOI
- https://doi.org/10.5705/ss.202026.0100
- Citations
- 1
- Primary Topic
- Spatial and Panel Data Analysis
- Type
- article
- Field-Weighted Citation Impact
- 3.11
Funders
- Agenția Națională pentru Cercetare și Dezvoltare
- Agencia Nacional de Investigación y Desarrollo
- CHIST-ERA