PURPOSES : This study was conducted to develop a traffic accident prediction model using traffic accident data and management and service evaluation data on bus companies in Busan, and to determine the possibility of establishing customized traffic accident prevention measures for each company.
METHODS: First, we collected basic data on the characteristics of urban bus traffic accidents and conducted basic statistical analysis. Then, we developed traffic accident prediction models using Poisson regression and negative binomial regression to examine the characteristics of major items of management and service evaluation affecting traffic accidents.
RESULTS : The Poisson regression model showed overdispersion; hence, the negative binomial regression model was selected. The results of the traffic accident prediction model developed using negative binomial regression are acceptable at 95% confidence level (a = 0.05).
CONCLUSIONS : The traffic accident prediction model indicates that the management of the traffic record system and internal and external management items in service evaluation have a significant effect on the reduction of traffic accidents. In particular, because human factors are the main cause of traffic accidents, bus traffic accidents are expected to greatly decrease if drivers' dangerous driving behaviors are effectively controlled by bus companies.

ABSTRACT
 1. 서론
  1.1. 연구의 필요성 및 목적
  1.2. 연구의 범위
  1.3. 연구의 방법
 2. 관련 이론 및 문헌 고찰
  2.1. 포아송 회귀모형
  2.2. 음이항 회귀모형
  2.3. 관련 연구 고찰
  2.4. 연구의 차별성
 3. 자료수집 및 변수선정
  3.1. 자료수집
  3.2. 변수 선정
  3.3. 변수 정의
  3.4. 변수 정보
  3.5. 상관분석
 4. 버스회사 교통사고 예측모형 개발
  4.1. 회귀 분석
  4.2. 분석 결과
  4.3. 시내버스 업체 교통사고 모형 활용 방안
 5. 결론 및 향후 연구과제
  5.1. 결론
  5.2. 향후 연구과제
 REFERENCES

• 박원일(한국운수산업연구원 연구원) | Park Wonil
• 김경현(한국교통안전공단) | Kim Kyung Hyun
• 박상민(아주대학교 건설교통공학과) | Park Sangmin
• 박성호(아주대학교 건설교통공학과) | Park Sungho
• 윤일수(아주대학교 교통시스템공학과) | Yun Ilsoo 교신저자