Comparing and Contrasting the Impacts of Macro-Level Factors on Crash Duration and Frequency

Abstract

Road traffic crashes cause social, economic, physical and emotional losses. They also reduce operating speed and road capacity and increase delays, unreliability, and productivity losses. Previous crash duration research has concentrated on individual crashes, with the contributing elements extracted directly from the incident description and records. As a result, the explanatory variables were more regional, and the effects of broader macro-level factors were not investigated. This is in contrast to crash frequency studies, which normally collect explanatory factors at a macro-level. This study explores the impact of various factors and the consistency of their effects on vehicle crash duration and frequency at a macro-level. Along with the demographic, vehicle utilisation, environmental, and responder variables, street network features such as connectedness, density, and hierarchy were added as covariates. The dataset contains over 95,000 vehicle crash records over 4.5 years in Greater Sydney, Australia. Following a dimension reduction of independent variables, a hazard-based model was estimated for crash duration, and a Negative Binomial model was estimated for frequency. Unobserved heterogeneity was accounted for by latent class models for both duration and frequency. Income, driver experience and exposure are considered to have both positive and negative impacts on duration. Crash duration is shorter in regions with a dense road network, but crash frequency is higher. Highly connected networks, on the other hand, are associated with longer length but lower frequency.

Prediction of Duration of Traffic Incidents by Hybrid Deep Learning Based on Multi-Source Incomplete Data

“…In 2022, instead of using the variables extracted from incident descriptions and records, Chand et al collected explanatory factors at a macro-level and used latent class models to estimate the crash duration and frequency for unobserved heterogeneity. The results showed that income, driver experience, and exposure are considered to have both positive and negative impacts on duration [ 23 ].…”

A Novel Explanatory Tabular Neural Network to Predicting Traffic Incident Duration Using Traffic Safety Big Data

“…Such models are based on the assumption that the duration of a traffic incident can be predicted by a set of factors, including the incident type, time of day, and prevailing weather conditions, as well as the traffic volume. These models encompass widely used regression models [6][7][8][9][10], probabilistic statistical models [11][12][13], hazard-based models [14][15][16][17][18], copula-based models [19], finite mixture models [20,21], etc. They typically assume that the data follow a certain distribution and model and predict the distribution of the data.…”

Nonlinear Analysis of the Effects of Socioeconomic, Demographic, and Technological Factors on the Number of Fatal Traffic Accidents

“…These factors include broader social, economic, and demographic conditions such as Gross Domestic Product (GDP), inflation rate, income levels, educational attainment, poverty rates, employment rates, average cost per mile traveled, daily vehicle miles traveled by drivers, and the extent of urban development in a particular area. Researchers have extensively studied these factors [5][6][7]. Previous studies have typically focused on individual contributing factors or a limited combination.…”