University of Khartoum

An Econometric Model For Road Crashes in Khartoum State

An Econometric Model For Road Crashes in Khartoum State

Show full item record

Title: An Econometric Model For Road Crashes in Khartoum State
Author: Omer Ali Ibrahim, Mohamed
Abstract: This research examines the trends, the characteristics of traffic accidents and sustaining injuries, in addition to the underlying factors behind them in Khartoum State during the period 1991-2007. The data of the study were collected from the Police reports, Insurance companies statistics, and a survey of 400 drivers. The research consists of both methodological and empirical work. A part of the methodological research is oriented towards time series and cross sectional modeling. This involves advanced econometric methods such as stationarity analysis , the State-Space methods , and DRAG models . The empirical work involves estimating accidents risk function using ARIMA models, regression models with ARMA errors, and logistic regression for the explanation and prediction of death, and fatal accidents and assessing risky behavior of drivers. The results suggested that traffic accidents are non-stationary and have seasonality with December, January, February, and March witnessing the highest rates. Law enforcement, and economic improvements, and awareness campaigns have contributed positively to reducing accidents. Also, risky behavior is widely prevalent among drivers represented in excessive speeding, lack of seat-belt and children restraint use, drink-driving, and using mobiles while driving. For reducing road accidents in Khartoum State, the research recommended a strategy including awareness campaigns, road maintenance and engineering improvements, safer vehicles, education and training for traffic police , traffic legislations concerning traffic safety such as seat belt use and children restraint.
URI: http://khartoumspace.uofk.edu/handle/123456789/12731
Date: 2015-06-15


Files in this item

Files Size Format View

This item appears in the following Collection(s)

Show full item record

Share

Search DSpace


Browse

My Account