• 대한교통학회지
• /
• 제31권1호
• /
• pp.65-76
• /
• 2013

사고발생의 주요지점인 신호교차로 교통사고 발생건수는 해마다 증가하고 있어 교통사고를 감소시키기 위한 원인 규명이 매우 필요하다. 국내에서 연구되어진 기존의 교통사고예측 모형들은 대부분 Poisson 모형 등의 비선형 회귀분석을 이용한 사고원인분석이 주를 이루고 있다. 비선형 Econometrics 분석기법들이 사고의 성격을 분석하는데 가장 중요한 통계적 기법이기는 하지만, 도로에서 발생하는 교통사고의 원인분석적 차원에서 접근하면 이런 사고예측 모형들만 가지고 사고발생의 설명변수들을 규명하는데 구조적인 한계가 발생한다. 이는 이러한 통계적 방법들이 사고의 예측력을 높이는데 중점을 두고, 이를 위해 소수의 유효한 설명변수들만을 모형식에 포함시키기 때문이다. 따라서 사고에 대해 보다 구체적인 원인규명을 위해서는 비선형회귀분석모형의 개발과 동시에 비선형 Econometrics 분석기법의 단점을 보완하는 또 다른 통계적 노력이 필요하다. 이에 본 연구에서는 Poisson기법을 이용하여 지방부 4지 신호교차로의 사고예측모형을 개발하였고, 동시에 복합적인 인과관계를 증명하는데 다중변수관계를 포괄적으로 측정하여 탐색하는 구조방정식을 이용하여 사고모형을 개발하여 Poisson 모형의 결과값과 비교 분석하였다.

• 한국안전학회지
• /
• 제23권2호
• /
• pp.65-71
• /
• 2008

As the interest in traffic safety has been increasing recently, social movement is being made to reduce the number of traffic accidents and the view on improving the mobility of the existing roads is being converted into on establishing traffic safety as a priority. The increase of traffic accidents related to an intersection in a state that traffic accidents are decreasing overall may suggests the necessity to investigate the specific causes. In addition, we have to consider them when establishing the measures against traffic accidents in a intersection by investigating and analyzing the influences and factors that may affect traffic accidents. To induce the accident severity model, we collected the factors that affect accidents and then applied the Poisson Regression Model among nonlinear regression analysis by verifying the distribution of variables. As a result of the analysis, it turned out that the volume of traffic on main roads, the right turn ratio on sub-roads, the number of ways out on sub-roads, the number of exclusive roads for a left turn, the signals for a right turn on main roads, and an intersect angle were the factors that affect the accident severity.

• 대한교통학회지
• /
• 제26권2호
• /
• pp.35-46
• /
• 2008

본 연구는 지방부의 교통사고 특성을 분석하고 사고모형을 개발하는데 그 목적이 있다. 이를 위해 본 연구에서는 청주시와 청원군의 신호교차로를 중심으로 다중선형, 포아송 및 음이항회귀모형을 개발하는데 중점을 두고 있다. 분석된 주요 연구결과는 다음과 같다. 첫째, 사고특성 분석을 통해 지방부 교통사고의 특성이 요인별로 파악되었다. 둘째, 통계적으로 설명력이 높은 4개의 사고모형이 개발되었다. 마지막으로 평균차로폭차($X_2$)와 교차로간거리 ($X_{11}$)가 지방부의 특성을 반영할 수 있는 특정변수로 밝혀졌다.

• 한국안전학회지
• /
• 제25권3호
• /
• pp.131-136
• /
• 2010

This study deals with the accident models of arterial link sections by vehicle type. The objectives are to analyze the characteristics of accidents, and to develop the models by type. In pursuing the above, this study uses the data of 414 accidents occurred on 24 major arterial links in 2007. The main results analyzed are as follows. First, the number of accidents is analyzed to account for about 47% in passenger car, 15% in SUV and 10% in trucks. Second, 3 Poisson regression models which are all statistically significant are developed using passenger car, SUV and truck as dependant variables. Finally, AADT and the number of traffic islands as common variables, and the number of pedestrian crossings, lanes, connecting roads, intersections(4-Leg), rate of medians and the number of bus stops as specific variables of the models are selected.

• 한국안전학회지
• /
• 제26권5호
• /
• pp.130-135
• /
• 2011

This study deals with the accident models of arterial road sections. The objectives is to develop the models by number of lane. In pursuing the above, this study gives particular emphasis to dividing the 474 small link sections, collecting the accident data of 2007, and applying the statistical programs of SPSS17.0 and NLOGIT4.0. The main results are as follows. First, the number of accidents of two-lane roads were analyzed to be 59.9% of totals and to be the most of all. Second, one Poisson and two negative binomial regression models which were all statistically significant were developed. Finally, the common variables of all models were evaluated to be ADT and number of exit/entry which were all positive to the accidents.

• Communications for Statistical Applications and Methods
• /
• 제29권2호
• /
• pp.239-250
• /
• 2022

In many applications, we frequently encounter correlated multiple outcomes measured on the same subject. Joint modeling of such multiple outcomes can improve efficiency of inference compared to independent modeling. For instance, in developmental toxicity studies, fetal weight and number of malformed pups are measured on the pregnant dams exposed to different levels of a toxic substance, in which the association between such outcomes should be taken into account in the model. The number of malformations may possibly have many zeros, which should be analyzed via zero-inflated count models. Motivated by applications in developmental toxicity studies, we propose a Bayesian joint modeling framework for continuous and count outcomes with excess zeros. In our model, zero-inflated Poisson (ZIP) regression model would be used to describe count data, and a subject-specific random effects would account for the correlation across the two outcomes. We implement a Bayesian approach using MCMC procedure with data augmentation method and adaptive rejection sampling. We apply our proposed model to dose-response analysis in a developmental toxicity study to estimate the benchmark dose in a risk assessment.

• 한국안전학회지
• /
• 제29권6호
• /
• pp.151-157
• /
• 2014

This study deals with the rear-end collision at roundabouts. The purpose of this study is to develop the accident models of rear-end collision in Korea. In pursuing the above, this study gives particular attention to developing the appropriate models using Poisson, negative binomial model, ZAM, multiple linear and nonlinear regression models, and statistical analysis tools. The main results are as follows. First, the Vuong statistics and overdispersion parameters indicate that ZIP is the most appropriate model among count data models. Second, RMSE, MPB, MAD and correlation coefficient tests show that the multiple nonlinear model is the most suitable to the rear-end collision data. Finally, such the independent variables as traffic volume, ratio of heavy vehicle, number of circulatory roadway lane, number of crosswalk and stop line are adopted in the optimal model.

• Journal of the Korean Data and Information Science Society
• /
• 제26권2호
• /
• pp.387-397
• /
• 2015

본 연구에서는 청년인턴 DB와 고용보험 DB를 사용하여 중소기업 청년인턴의 이직횟수에 영향을 미치는 요인을 분석하였다. 이직횟수는 음수가 아닌 정수 값만 가지는 계수 데이터 (count data)이므로 일반적인 선형회귀모형을 적용하는 것은 문제가 있다. 따라서 계수 데이터에 적합한 회귀모형으로 포아송 회귀모형, 영과잉 포아송 회귀모형, 음이항 회귀모형, 영과잉 음이항 회귀모형 등 4개의 회귀모형을 적용하였다. 분석결과 최적모형으로 영과잉 음이항 회귀모형이 선택되었다. 주요 분석결과를 정리하면 다음과 같다. 첫째, 통제집단 (비인턴집단)에 비해서 처리집단 (인턴집단)이 통계적으로 유의하게 이직경험이 낮게 나타났다. 둘째, 연령이 작을수록 통계적으로 유의하게 이직경험이 낮게 나타났다. 셋째, 여자에 비해서 남자가 유의하게 이직횟수가 높게 나타났다. 마지막으로 기업규모가 클수록 이직횟수가 유의하게 감소하는 것으로 나타났다.

• Journal of Preventive Medicine and Public Health
• /
• 제55권4호
• /
• pp.371-378
• /
• 2022

Objectives: No studies have examined the association between preterm birth rates and socioeconomic factors in Japan using nationwide statistical data. We analyzed the association between preterm birth rates and household occupation using Vital Statistics data. Methods: Aggregated Vital Statistics data from Japan from 2007 to 2019 were obtained from the Ministry of Health, Labour and Welfare. From the data, the number of births according to year, age group, gestational period, number of pregnancies, and household occupation were used in this study. Crude preterm birth rates and preterm birth rates adjusted by maternal age according to household occupation were calculated for each year. Poisson regression analysis was conducted to evaluate the association between household occupation and preterm births. Results: Unemployed households had the highest preterm birth rate, and households with an occupation classification of "full-time worker 2" (an employee at a large company, civil servant, or board member) had the lowest preterm birth rate throughout each period. Poisson regression analysis revealed that unemployed households were statistically significantly associated with a high preterm birth risk. In contrast, the preterm birth rate adjusted by maternal age remained stable throughout each period regardless of household occupation, and preterm birth rates were found not to have increased in recent years in Japan. Conclusions: Unemployed households had higher preterm birth rates than other household occupations. Further studies investigating the characteristics of unemployed households are needed to identify the reasons for this disparity.

• 대한안전경영과학회지
• /
• 제15권2호
• /
• pp.9-20
• /
• 2013

OSHA(Occupational Safety and Health Act) generally regulates employer's business principles in the workplace to maintain safety environment. This act has the fundamental purpose to protect employee's safety and health in the workplace by reducing industrial accidents. Authors tried to investigate the correlation between 'occupational injuries and illnesses' and level of regulation compliance using Survey on Current Status of Occupational Safety & Health data by the various statistical methods, such as generalized regression analysis, logistic regression analysis and poison regression analysis in order to compare the results of those methods. The results have shown that the significant affecting compliance factors were different among those statistical methods. This means that specific interpretation should be considered based on each statistical method. In the future, relevant statistical technique will be developed considering the distribution type of occupational injuries.