Details
| Original language | English |
|---|---|
| Article number | 100490 |
| Journal | Spatial statistics |
| Volume | 41 |
| Publication status | Published - Mar 2021 |
| Externally published | Yes |
Abstract
In contrast to classical econometric approaches which are based on prespecified isotropic weighting schemes, we suggest that the spatial weighting matrix in the presence of directional dependencies should be estimated. We identify this direction based on different candidate neighbourhood sets. In this paper, we consider two different types of processes – namely spatial autoregressive and spatial autoregressive conditional heteroscedastic processes – and derive the consistency of the corresponding maximum likelihood estimates in the presence of directional dependencies. Moreover, Monte Carlo simulation results indicate that the model's performance improves with sample size and with smaller neighbourhood subset sizes. Finally, we apply this approach to aerosol observations over the North Atlantic region and show that their spatial dependence matches the direction of the trade winds in this area.
Keywords
- Directional spatial dependencies, Regular lattice data, Spatial AR and ARCH processes, Spatial weights matrix
ASJC Scopus subject areas
- Mathematics(all)
- Statistics and Probability
- Earth and Planetary Sciences(all)
- Computers in Earth Sciences
- Environmental Science(all)
- Management, Monitoring, Policy and Law
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Spatial statistics, Vol. 41, 100490, 03.2021.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Directional spatial autoregressive dependence in the conditional first- and second-order moments
AU - Merk, M.S.
AU - Otto, P.
N1 - Publisher Copyright: © 2020 Elsevier B.V.
PY - 2021/3
Y1 - 2021/3
N2 - In contrast to classical econometric approaches which are based on prespecified isotropic weighting schemes, we suggest that the spatial weighting matrix in the presence of directional dependencies should be estimated. We identify this direction based on different candidate neighbourhood sets. In this paper, we consider two different types of processes – namely spatial autoregressive and spatial autoregressive conditional heteroscedastic processes – and derive the consistency of the corresponding maximum likelihood estimates in the presence of directional dependencies. Moreover, Monte Carlo simulation results indicate that the model's performance improves with sample size and with smaller neighbourhood subset sizes. Finally, we apply this approach to aerosol observations over the North Atlantic region and show that their spatial dependence matches the direction of the trade winds in this area.
AB - In contrast to classical econometric approaches which are based on prespecified isotropic weighting schemes, we suggest that the spatial weighting matrix in the presence of directional dependencies should be estimated. We identify this direction based on different candidate neighbourhood sets. In this paper, we consider two different types of processes – namely spatial autoregressive and spatial autoregressive conditional heteroscedastic processes – and derive the consistency of the corresponding maximum likelihood estimates in the presence of directional dependencies. Moreover, Monte Carlo simulation results indicate that the model's performance improves with sample size and with smaller neighbourhood subset sizes. Finally, we apply this approach to aerosol observations over the North Atlantic region and show that their spatial dependence matches the direction of the trade winds in this area.
KW - Directional spatial dependencies
KW - Regular lattice data
KW - Spatial AR and ARCH processes
KW - Spatial weights matrix
UR - http://www.scopus.com/inward/record.url?scp=85099201890&partnerID=8YFLogxK
U2 - 10.1016/j.spasta.2020.100490
DO - 10.1016/j.spasta.2020.100490
M3 - Article
VL - 41
JO - Spatial statistics
JF - Spatial statistics
SN - 2211-6753
M1 - 100490
ER -