Related Experiment Video
Updated: Jun 8, 2025

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street
Published on: January 20, 2023
A spatial autocorrelation analysis of road traffic accidents by severity using Moran's I spatial statistics: a study
Roshan Kumar Mahato1, Kyaw Min Htike1, Kittipong Sornlorm2
1Faculty of Public Health, Khon Kaen University, Khon Kaen, Thailand.
Background:
Road traffic accidents (RTAs) are a significant global public health issue, leading to injuries, fatalities, and substantial economic losses. In Nepal, RTAs are a major concern, with notable regional variations in incidence and severity. This study analyzed the spatial distribution and types of road traffic injuries in Nepal from Fiscal Year (FY) 2019-2020 to 2021-2022, focusing on the impact of road types and geographic factors.
Methods:
The study covers all 77 districts of Nepal, incorporating diverse geographic and climatic regions. Data on RTAs, including fatal and non-fatal injuries, were obtained from the Kathmandu Valley Traffic Police Office, Nepal. Spatial analysis was conducted using Quantum GIS (QGIS) and GeoDa software. Univariate and bivariate risk factor analyses were performed using Moran's I statistics to detect spatial autocorrelation in RTA severity.
Results:
The overall fatality rate increased from 7.70 to 9.89 per 100,000 population from FY 2019-2020 to 2021-2022. However, spatial clustering of crashes showed a decline over the years. In FY 2019-2020 (Moran's I; 0.276, p-value; 0.001), moderate clustering was observed, which weakened in the subsequent years (Moran's I; 0.127, p-value; 0.002), with a near-random distribution by FY 2021-2022 (Moran's I; -0.015, p-value; 0.457). The analysis of crash severity revealed significant variations across districts, with high fatality rates in remote areas like Mustang and Mugu, and low rates in districts such as Manang.
Road Network Analysis:
The study examined the impact of different road types on RTA severity. Bitumen (BT) roads showed a negative correlation with RTA rates, while Earthen Roads (ER) were positively associated with higher RTA rates. Hot-spot and cold-spot clusters were identified for each road type, highlighting higher or lower RTA severity areas.
Conclusion:
This study provides valuable insights into the spatial patterns of RTAs in Nepal and the influence of road types on accident severity. The findings emphasize the need for targeted road safety interventions and infrastructure improvements, particularly in high-risk areas. By understanding spatial distributions and road network impacts, policymakers can better address road safety challenges and reduce the incidence of RTAs in Nepal.
Related Concept Videos
Manipulation and Analysis
Hypothesis Test for Test of Independence
H0: The two variables (factors)...
Design Example: Alignment of a Road Line Using GIS
Determination of Expected Frequency
Statistical Methods for Analyzing Epidemiological Data
Correlation
Two variables, for example, a and b, are said to be positively correlated if both variables move in the same direction. In other words, a positive correlation exists between two variables, a and b, if:

