DOI QR코드

DOI QR Code

A Study on Developing Crash Prediction Model for Urban Intersections Considering Random Effects

임의효과를 고려한 도심지 교차로 교통사고모형 개발에 관한 연구

  • Received : 2014.12.05
  • Accepted : 2015.01.07
  • Published : 2015.02.28

Abstract

Previous studies have estimated crash prediction models with the fixed effect model which assumes the fixed value of coefficients without considering characteristics of each intersections. However the fixed effect model would estimate under estimation of the standard error resulted in over estimation of t-value. In order to overcome these shortcomings, the random effect model can be used with considering heterogeneity of AADT, geometric information and unobserved factors. In this study, data collections from 89 intersections in Daejeon and estimates of crash prediction models were conducted using the random and fixed effect negative binomial regression model for comparison and analysis of two models. As a result of model estimates, AADT, speed limits, number of lanes, exclusive right turn pockets and front traffic signal were found to be significant. For comparing statistical significance of two models, the random effect model could be better statistical significance with -1537.802 of log-likelihood at convergence comparing with -1691.327 for the fixed effect model. Also likelihood ration value was computed as 0.279 for the random effect model and 0.207 for the fixed effect model. This mean that the random effect model can be improved for statistical significance of models comparing with the fixed effect model.

기존의 교통사고모형은 수집된 데이터에 대한 추정된 모수가 고정되어있다고 가정하여 교통량이나 기하구조의 길이와 폭 등은 설치형태와 관계없이 동일한 값을 적용하는 고정효과모형을 이용하여 개발하였다. 하지만 고정효과를 이용한 모형은 모형을 통해 추정된 계수의 표준오차 값이 과소 추정되거나 각 계수의 t-값이 과도하게 산정되어 모형의 설명력이 낮아지게 된다. 이를 극복하기 위하여 교통량, 기하구조, 그리고 관측되지 않은 다른 요인 등에 대한 이질성을 고려한 임의효과모형을 활용하여 모형을 개발할 수 있다. 본 연구에서는 임의효과모형의 효용성을 파악하고자 대전광역시 주요 89개 교차로를 대상으로 데이터를 수집하여 임의효과와 고정효과를 이용한 음이항 회귀모형을 개발하고 이를 비교 분석하였다. 모형개발 결과 년평균일교통량, 제한속도, 차로수, 우회전 전용차로 설치유무, 전방신호등 설치유무 등이 유효한 설명변수로 나타났으며 모형의 설명력을 비교해보면 로그-우도함수값이 임의효과에서 -1537.802로 고정효과의 로그-우도함수값 -1691.327보다 모형 설명력이 좋은 것으로 나타났으며 우도비의 경우 임의효과에서 0.279로 고정효과의 0.207보다 개선된 것으로 나타나 임의효과를 이용한 모형이 고정효과를 이용한 모형보다 우수한 것으로 나타났다.

Keywords

References

  1. P. P. Jovanie, and H. Chang, "Modeling the relationship of accidents to miles traveled", Transportation Research Record, 1068, pp.42-51, 2002.
  2. S. P. Miaou, and H. A. Lum, "Modeling vehicle accidents and highway geometric design relationship", Accident Analysis & Prevention, vol. 25, no. 6, pp.689-709, 1993. https://doi.org/10.1016/0001-4575(93)90034-T
  3. S. B. Jeong, B. H. Hwang, N. M. Sung, and S. H. Lee, "Development of evaluation model for black spot improvement priorities by using empirical bayes method", Journal of Korean Society of Transportation, vol. 27, no. 3, pp.81-90, 2009.
  4. S. H. Lee, Y. D. Lee, and M. S. Do, "Safety impacts of red light enforcement on signalized intersections", Journal of the Korean Society of Transportation, vol. 30, no. 6, pp.93-102, 2012. https://doi.org/10.7470/jkst.2012.30.6.093
  5. D. Lord, S. P. Washington, and J. N. Ivan, "Poisson, Poisson-Gamma and zero-inflated regression models of motor vehicle crashes: balancing statistical fit and theory", Accident Analysis & Prevention, vol. 37, no. 1, pp.35-46, 2005. https://doi.org/10.1016/j.aap.2004.02.004
  6. S. Washington, and K. Shin, "The impact of red light camera (automated enforcement) on safety in Arizona", FHWA-AZ-05-550, Arizona Department of Transportation, 2005.
  7. H. C. Chin, and M. A. Quddus, "Applying the random effect negative binomial model to examine traffic accident occurrence at signalized intersection", Accident Analysis & Prevention, vol. 35, no. 2, pp.253-259, 2003. https://doi.org/10.1016/S0001-4575(02)00003-9
  8. M. H. Park, "Relationship between interstate highway accident and heterogeneous geometrics by random parameter negative binomial model-a case of interstate highway in Washington state, USA", Journal of the Korean Society of Transportation, vol. 33, no. 6, pp.2437-2445, 2013.
  9. N. S. Venkataraman, G. F. Ulfarsson, S. Venky, J. Oh, and M. Park, "Model of relationship between interstate crash occurrence and geometrics", Transportation Research Record, 2236, pp.41-48, 2011. https://doi.org/10.3141/2236-05
  10. P. C. Anastasopoulos, and F. L. Mannering, "A note on modeling vehicle accident frequencies with random-parameters count models", Accident Analysis & Prevention, vol. 41, no. 1, pp.153-159, 2009. https://doi.org/10.1016/j.aap.2008.10.005
  11. W. Greene, "Limdep, Version 9.0. Econometric Sftware Inc.", Plainveiw, NY., 2007.
  12. P. Greibe, "Accident prediction models for urban roads", Accident Analysis & Prevention, vol. 35, pp.273-285, 2003. https://doi.org/10.1016/S0001-4575(02)00005-2

Cited by

  1. A Meta Analysis of the Effects of Road Safety Facilities on Accident Reduction: Focusing on Signalized Intersection vol.34, pp.4, 2016, https://doi.org/10.7470/jkst.2016.34.4.291
  2. A Development of Traffic Accident Prediction Model at Rural Unsignalized Intersections Using Random Parameter vol.16, pp.4, 2017, https://doi.org/10.12815/kits.2017.16.4.64
  3. A Study on the Improvement of Prediction Accuracy for Traffic Accident Models Using Machine Learning (Generalized Regression Neural Network) vol.20, pp.6, 2018, https://doi.org/10.7855/IJHE.2018.20.6.179
  4. 영과잉을 고려한 중심상업지구 교통사고모형 개발에 관한 연구 vol.18, pp.4, 2015, https://doi.org/10.7855/ijhe.2016.18.4.083
  5. For Preventative Automated Driving System (PADS): Traffic Accident Context Analysis Based on Deep Neural Networks vol.9, pp.11, 2015, https://doi.org/10.3390/electronics9111829