Analysis of Crash Frequency and Crash Severity in Thailand: Hierarchical Structure Models Approach

Abstract

Currently, research on the development of crash models in terms of crash frequency on road segments and crash severity applies the principles of spatial analysis and heterogeneity due to the methods’ suitability compared with traditional models. This study focuses on crash severity and frequency in Thailand. Moreover, this study aims to understand crash frequency and fatality. The result of the intra-class correlation coefficient found that the spatial approach should analyze the data. The crash frequency model’s best fit is a spatial zero-inflated negative binomial model (SZINB). The results of the random parameters of SZINB are insignificant, except for the intercept. The crash frequency model’s significant variables include the length of the segment and average annual traffic volume for the fixed parameters. Conversely, the study finds that the best fit model of crash severity is a logistic regression with spatial correlations. The variances of random effect are significant such as the intersection, sideswipe crash, and head-on crash. Meanwhile, the fixed-effect variables significant to fatality risk include motorcycles, gender, non-use of safety equipment, and nighttime collision. The paper proposes a policy applicable to agencies responsible for driver training, law enforcement, and those involved in crash-reduction campaigns.

Accident Frequency Prediction Model for Flat Rural Roads in Serbia

“…There was a particularly large deviation of the MSPE compared to the other models. It should be emphasized that this outcome was expected-given a small number of zeros in the observed data set (31.07%), contrary to the earlier research in which the percentage of zeros was greater than 80% [29] and, therefore, the zero-inflated models were superior compared to the Poisson and NB models. However, Lord et al [30] claimed that the excess zeros in a data set can be the consequence of (1) the existence of sites with a combination of low exposures and high heterogeneities, (2) analyses conducted with too small spatial or time scales, (3) data with relatively high percentages of missing or unreported accidents, or (4) the application of a model with important predictive variables omitted.…”

“…Another problem that occurs in accident frequency modeling is excess zeros in the observations, due to the fact that traffic accidents are rare events. The Poisson and NB models tend to produce erroneous estimates for over-dispersed accident data when there are large numbers of zeros in a data set; thus, zero-inflated Poisson (ZIP) and zero-inflated negative binomial (ZINB) models are more adequate [29]. However, the problem with the inflated models is in the assumption of a dual state.…”

“…Many studies have found that accident frequency is affected by the segment length [21,24,29,32], lane width [29,40], lane numbers [27,32,38], carriageway width [21,29,41], and the shoulder width and type [29,42]. Significant attention has been dedicated to horizontal and vertical road geometric elements, which are found to affect the accident frequency [28,37,43,44].…”

“…Moreover, they determined that horizontal curves with higher design speeds have larger effects on the accident frequency than curves with lower design speeds, due to risk compensation by the drivers. The effects of horizontal curves have been investigated through various elements; it was found that a larger horizontal curvature [27], a smaller radius of a horizontal curve [29,46], a greater angle of a curvature [28,47], and a shorter horizontal curve [46], increase the accident frequency. Huo et al [48] claimed that the number of accidents increases with the increase in the longitudinal grade.…”

Modelling Road Accident Fatalities with Underdispersion and Zero-inflated Counts

“…The number of RTAs increased significantly with the higher volume of rainfall in the Southern and Northern provinces during 2012-2018 [14]. Such figures on Thai highways for 2011-2017 were affected by the length of the segment and average annual traffic volume [15]. Road type, road section and festive month were crucial factors relating to the number of injuries on roads [16].…”