Back to Search
Start Over
A class of multi-resolution approximations for large spatial datasets
- Source :
- Statistica Sinica, 30(4), 2203-2226 (2020)
- Publication Year :
- 2017
-
Abstract
- Gaussian processes are popular and flexible models for spatial, temporal, and functional data, but they are computationally infeasible for large datasets. We discuss Gaussian-process approximations that use basis functions at multiple resolutions to achieve fast inference and that can (approximately) represent any spatial covariance structure. We consider two special cases of this multi-resolution-approximation framework, a taper version and a domain-partitioning (block) version. We describe theoretical properties and inference procedures, and study the computational complexity of the methods. Numerical comparisons and an application to satellite data are also provided.
- Subjects :
- Statistics - Methodology
Statistics - Computation
Subjects
Details
- Database :
- arXiv
- Journal :
- Statistica Sinica, 30(4), 2203-2226 (2020)
- Publication Type :
- Report
- Accession number :
- edsarx.1710.08976
- Document Type :
- Working Paper
- Full Text :
- https://doi.org/10.1007/s13253-020-00401-7