Details
| Original language | English |
|---|---|
| Pages (from-to) | 368-410 |
| Number of pages | 43 |
| Journal | Transactions in GIS |
| Volume | 28 |
| Issue number | 2 |
| Publication status | Published - 10 Apr 2024 |
Abstract
Contemporary spatial statistics studies often underestimate the complexity of road networks, thereby inhibiting the strategic development of effective interventions for car accidents. In response to this limitation, the primary objective of this study is to enhance the spatiotemporal analysis of urban crash data. We introduce an innovative spatial-temporal weight matrix (STWM) for this purpose. The STWM integrates external covariates, including road network topological measurements and economic variables, offering a more comprehensive view of the spatiotemporal dependence of road accidents. To evaluate the functionality of the presented STWM, random effect eigenvector spatial filtering analysis is employed on Boston's traffic accident data from January to March 2016. The STWM improves analysis, surpassing distance-based SWM with a lower residual standard error of 0.209 and a higher adjusted R2 of 0.417. Furthermore, the study emphasizes the influence of road length on crash incidents, spatially and temporally, with random standard errors of 0.002 for spatial effects and 0.026 for non-spatial effects. This is particularly evident in the north and center of the study area during specific periods. This information can help decision-makers develop more effective urban development models and reduce future crash risks.
ASJC Scopus subject areas
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Transactions in GIS, Vol. 28, No. 2, 10.04.2024, p. 368-410.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Analyzing urban crash incidents
T2 - An advanced endogenous approach using spatiotemporal weights matrix
AU - Mohammadi, Reza
AU - Taleai, Mohammad
AU - Otto, Philipp
AU - Sester, Monika
PY - 2024/4/10
Y1 - 2024/4/10
N2 - Contemporary spatial statistics studies often underestimate the complexity of road networks, thereby inhibiting the strategic development of effective interventions for car accidents. In response to this limitation, the primary objective of this study is to enhance the spatiotemporal analysis of urban crash data. We introduce an innovative spatial-temporal weight matrix (STWM) for this purpose. The STWM integrates external covariates, including road network topological measurements and economic variables, offering a more comprehensive view of the spatiotemporal dependence of road accidents. To evaluate the functionality of the presented STWM, random effect eigenvector spatial filtering analysis is employed on Boston's traffic accident data from January to March 2016. The STWM improves analysis, surpassing distance-based SWM with a lower residual standard error of 0.209 and a higher adjusted R2 of 0.417. Furthermore, the study emphasizes the influence of road length on crash incidents, spatially and temporally, with random standard errors of 0.002 for spatial effects and 0.026 for non-spatial effects. This is particularly evident in the north and center of the study area during specific periods. This information can help decision-makers develop more effective urban development models and reduce future crash risks.
AB - Contemporary spatial statistics studies often underestimate the complexity of road networks, thereby inhibiting the strategic development of effective interventions for car accidents. In response to this limitation, the primary objective of this study is to enhance the spatiotemporal analysis of urban crash data. We introduce an innovative spatial-temporal weight matrix (STWM) for this purpose. The STWM integrates external covariates, including road network topological measurements and economic variables, offering a more comprehensive view of the spatiotemporal dependence of road accidents. To evaluate the functionality of the presented STWM, random effect eigenvector spatial filtering analysis is employed on Boston's traffic accident data from January to March 2016. The STWM improves analysis, surpassing distance-based SWM with a lower residual standard error of 0.209 and a higher adjusted R2 of 0.417. Furthermore, the study emphasizes the influence of road length on crash incidents, spatially and temporally, with random standard errors of 0.002 for spatial effects and 0.026 for non-spatial effects. This is particularly evident in the north and center of the study area during specific periods. This information can help decision-makers develop more effective urban development models and reduce future crash risks.
UR - http://www.scopus.com/inward/record.url?scp=85190300331&partnerID=8YFLogxK
U2 - 10.1111/tgis.13138
DO - 10.1111/tgis.13138
M3 - Article
AN - SCOPUS:85190300331
VL - 28
SP - 368
EP - 410
JO - Transactions in GIS
JF - Transactions in GIS
SN - 1361-1682
IS - 2
ER -