Accident prediction models with random corridor parameters

El-Basyouny, Karim; Sayed, Tarek

doi:10.1016/j.aap.2009.06.025

Cited by 189 publications

(82 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there is potential by allowing some or all parameters to vary across observations, to account for heterogeneity across observations; for this reason, later research on general accident models (not at roundabouts) has used random-parameters; random-parameters models can be viewed as an extension of random-effects models. Rather than only influencing the intercept of the model, random-parameter models allow some or all estimated parameters, including traffic and geometric variables, to vary across observations (22) (23) (24) (25) (26). These authors found that some variables vary across roadway segments.…”

Section: Introductionmentioning

confidence: 99%

Roundabout Accident Prediction Model: Random-Parameter Negative Binomial Approach

Kamla

Parry

Dawson

2016

Transportation Research Record

View full text Add to dashboard Cite

Roundabouts have been widely used in the UK on all road classes, as they are generally considered safer than other types of intersections. The objective of this study is to examine geometric and traffic characteristics and their influence on accident numbers.The study comprises 70 roundabouts (284 approaches). The data used included all recorded vehicle accidents, geometric, and traffic characteristics for whole roundabouts, within the circulatory lanes, and at approaches to the roundabouts. Random-parameters negative binomial count data models were used to estimate model parameters and the models were compared with fixed-parameters negative binomial count data models.The random-parameters models provide better goodness of fit and more variables were found to be significant, relative to the fixed-parameters model. Total approach traffic, truck percentage, entry width, inscribed circle diameter, number of lanes, and presence of traffic signals were found as significant variables influencing accident occurrences.Keywords: Roundabout, accidents, random-parameters, fixed-parameters Kamla, Parry, Dawson 2 INTRODUCTIONRoundabout numbers continue to rise in countries and regions where they are already common, and especially, they are earning popularity in places where there were few roundabouts in the past. With respect to traffic operations and safety, roundabouts are often favoured over other intersection types. The use of roundabouts can improve safety by reducing or changing conflict types, reducing accident severity, and leading drivers to reduce speeds (1) (2) (3) (4). Various studies have analysed the safety of roundabouts, with a significant observed reduction in the number of accidents when intersections were converted to roundabouts (5) (6) (7) (8) (9) (10) (11) (12).Geometric layout, operational analysis and safety evaluation, are significant recurring requirements for roundabout design. Small modifications in geometry can lead to considerable changes in the safety and/or operational performance of roundabouts. The Highway Safety Manual (HSM) (13) uses traffic volume as a major input into the base condition safety performance function. Roundabouts, as substitute intersections, are likely to exhibit a similar traffic volume influence on their anticipated safety performance. Many studies have been undertaken to predict accident models depending on geometric and traffic variables using count data (Poisson or negative binomial models) (14) (15) (16) (17) (18) (19) (20). However, these studies assumed that variables (geometric and traffic) are constant across the observations (roundabouts). In some cases constraining the parameters to be constant when they actually vary across observations could lead to inconsistent and biased parameter estimates (21). However, there is potential by allowing some or all parameters to vary across observations, to account for heterogeneity across observations; for this reason, later research on general accident models (not at roundabouts) has used random-parameters; random...

show abstract

Section: Introductionmentioning

confidence: 99%

Roundabout Accident Prediction Model: Random-Parameter Negative Binomial Approach

Kamla

Parry

Dawson

2016

Transportation Research Record

View full text Add to dashboard Cite

show abstract

“…On the other side, CART method cannot solve some issues that NB regression model deals with, e.g. the marginal effects and elasticity from NB regression model can provide insights into the analysis process, the heterogeneity of accidents modelling can be addressed by random-parameter NB models [18,19], and temporal and spatial analysis of accidents, the endogeneity and heterogeneity issues can be interpreted by panel data random-parameter NB model and panel data simultaneous equation models [20,21]. Therefore, further exploration of CART method might provide a better understanding of the influencing factors of incident frequency for highways and intersections.…”

Section: Resultsmentioning

confidence: 99%

Freeway Incident Frequency Analysis Based on CART Method

Šarić

Kouhpanejade

2014

PROMET

View full text Add to dashboard Cite

show abstract

“…It should be noted that several mixedPoisson and random parameters Poisson models have recently been applied to account for heterogeneity [42 -46]. The random parameters model assumed that some or all of the parameters may be random because of unobserved variations or unobserved heterogeneity [43,44]. However, preliminary analyses found no significant unobserved heterogeneity (no statistically significant scale parameter or variance for all coefficients).…”

Section: Methodsmentioning

confidence: 99%