• Journal of the Korean Society of Safety
• /
• v.26 no.5
• /
• 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.

• The Korean Journal of Applied Statistics
• /
• v.31 no.6
• /
• pp.733-749
• /
• 2018

Sample selection arises as a result of the partial observability of the outcome of interest in a study. Heckman introduced a sample selection model to analyze such data and proposed a full maximum likelihood estimation method under the assumption of normality. Recently sample selection models for binomial and Poisson response variables have been proposed. Based on the theory of symmetry-modulated distribution, we extend these to a model for overdispersed count data. This type of data with no sample selection is often modeled using negative binomial distribution. Hence we propose a sample selection model for overdispersed count data using the negative binomial distribution. A real data application is employed. Simulation studies reveal that our estimation method based on profile log-likelihood is stable.

• 한국ITS학회:학술대회논문집
• /
• v.2007 no.10
• /
• pp.92-99
• /
• 2007

• International Journal of Highway Engineering
• /
• v.11 no.2
• /
• pp.151-158
• /
• 2009

This study deals with the rear-end collisions in the rural aiea. The objectives of this study are 1) to analyze the characteristics of rear-end accidents of signalized intersections, and 2) to develop the accident models for Cheongju-Cheongwon. In pursing the above, this study gives the particular attentions to comparing the characters of urban and rural area. In this study, the dependent variables are the number of accidents and value of EPDO(equivalent property damage only), and independent variables are the traffic volumes and geometric elements. The main results analyzed are the followings. First, the statistical analyses show that the Poisson accident model using the number of accident as a dependant variable are statistically significant and the negative binomial accident model using the value of EPDO are statistically significant. Second, the independent variables of Poisson model are analyzed to be the ratio of high-occupancy vehicles, total traffic volume and the sum of exit/entry, and those of negative binomial regression are the main road width, total traffic volume and the ratio of high-occupancy vehicles. Finally, the specific independent variables to the rural area are the main road width, the ratio of high occupancy vehicle, and the sum exit/entry.

• Health Policy and Management
• /
• v.25 no.4
• /
• pp.285-294
• /
• 2015

Background: Suicide is one of important health problems in Korea. Previous studies showed factors associated with suicide in individual levels. However, suicide was influenced by society that individuals belong to, so it was required to analyze suicide in local levels. The purpose of this study was to analyze the regional disparities of suicide mortality by gender and the association between local characteristics and suicide mortality. Methods: This study included 229 city county district administrative districts in Korea. Age- and sex-standardized suicide mortality and age-standardized suicide mortality (male/female) were used as dependent variables. City county district types, socio-demographics (number of divorces per 1,000 population, number of marriages per 1,000 population, and single households), financial variable (financial independence), welfare variable (welfare budget), and health behavior/status (perceived health status scores and EuroQol-5 dimension [EQ-5D]) were used to represent the local characteristics. We used hot-spot analysis to identify the spatial patterns of suicide mortality and negative binomial regression analysis to examine factors affecting suicide mortality. Results: There were differences in distribution of suicide mortality and hot-spot regions of suicide mortality by gender. Negative binomial regression analysis provided that city county district types (city), number of divorces per 1,000 population, financial independence, and EQ-5D had significant influences on the age- and sex-standardized suicide mortality per 100,000. Factor influencing suicide mortality was the number of divorces per 1,000 population in both male and female. Conclusion: Study results provided evidences that suicide mortality among regions was differed by gender. Health policy makers will need to consider gender and local characteristics when making policies for suicides.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.4
• /
• pp.14-25
• /
• 2018

In recent years, it has become technically easier to explain factors related with traffic accidents in the Big Data era. Therefore, it is necessary to apply the latest analysis techniques to analyze the traffic accident data and to seek for new findings. The purpose of this study is to compare the predictive performance of the negative binomial regression model and the deep learning method developed in this study to predict the frequency of traffic accidents in expressways. As a result, the MOEs of the deep learning model are somewhat superior to those of the negative binomial regression model in terms of prediction performance. However, using a deep learning model could increase the predictive reliability. However, it is easy to add other independent variables when using deep learning, and it can be expected to increase the predictive reliability even if the model structure is changed.

• Health Policy and Management
• /
• v.26 no.4
• /
• pp.343-351
• /
• 2016

Background: This study aims to analyze the effects of insurance types on the medical service uses for heart failure inpatients using propensity score matching (PSM). Methods: 2014 National inpatient sample based on health insurance claims data was used in the analysis. PSM was applied to control factors influencing the service uses except insurance types. Negative binomial regression was used after PSM to analyze factors that had influences on the service uses among inpatients. Subjects were divided by health insurance type, national health insurance (NHI) and medical aid (MA). Total charges and length of stay were used to represent the medical service uses. Covariance variables in PSM consist of sociodemographic characteristics (gender, age, Elixhauser comorbidity index) and hospital characteristics (hospital types, number of beds, location, number of doctors per 50 beds). These variables were also used as independent variables in negative binomial regression. Results: After the PSM, length of stay showed statistically significant difference on medical uses between insurance types. Negative binomial regression provided that insurance types, Elixhauser comorbidity index, and number of doctors per 50 beds were significant on the length of stay. Conclusion: This study provided that the service uses, especially length of stay, were differed by insurance types. Health policy makers will be required to prepare interventions to narrow the gap of the service uses between NHI and MA.

• Journal of the Korean Society of Safety
• /
• v.29 no.5
• /
• pp.154-159
• /
• 2014

This study deals with the pedestrian accidents of intersections in case of Cheongju. The objective is to develop the pedestrian accident models using Tobit regression model. In pursuing the above, the pedestrian accident data from 2007 to 2011 were collected from TAAS data set of Road Traffic Authority. To analyze the accident, Poisson, negative binomial and Tobit regression models were utilized in this study. The dependent variable were the number of accident by intersection. Independent variables are traffic volume, intersection geometric structure and the transportation facility. The main results were as follows. First, Tobit model was judged to be more appropriate model than other models. Also, these models were analyzed to be statistically significant. Second, such the main variables related to accidents as traffic volume, pedestrian volume, number of traffic island, crossing length and the pedestrian countdown signal systems were adopted in the above model.

• International Journal of Highway Engineering
• /
• v.20 no.2
• /
• pp.67-74
• /
• 2018

PURPOSES : The goal of this study is the development of roundabout accident models for urban and non-urban areas. METHODS : This study performed a comparative analysis of the regional factors affecting accidents. Traffic accident data were collected for the period 2010~2014 from the TAAS data set of the Road Traffic Authority. To develop the roundabout accident models, the Poisson and negative binomial regression models were used. A total of 25 explanatory variables such as geometry, and traffic volume were used. RESULTS : The key findings are as follows: First, it was found that the null hypotheses that the number of accidents is the same should be rejected. Second, three Poisson regression accident models, which are statistically significant (${\rho}^2$ of 0.154 and 0.385) were developed. Third, it was noted that although the common variable of the three models (models I~III) is the number of entry lanes, the specific variables are entry lane width, roundabout sign, number of circulatory roadways, splitter island, number of exit lanes, exit lane width, number of approach roads, and truck apron. CONCLUSIONS : The results of this study can provide suggestive countermeasures for decreasing the number of roundabout accidents.

• The Korean Journal of Applied Statistics
• /
• v.21 no.4
• /
• pp.603-613
• /
• 2008

We often encounter the situation that discrete count data have a large portion of zeros. In this case, it is not appropriate to analyze the data based on standard regression models such as the poisson or negative binomial regression models. In this article, we consider Bayesian analysis for two commonly used models. They are zero-inflated poisson and negative binomial regression models. We use the Bayes factor as a model selection tool and computation is proceeded via Markov chain Monte Carlo methods. Crash count data are analyzed to support theoretical results.