• The Korean Journal of Applied Statistics
• /
• v.31 no.3
• /
• pp.367-382
• /
• 2018

Prediction models for a corporate bond rating in existing studies have been developed using various models such as linear regression, ordered logit, and random forest. Financial characteristics help build prediction models that are expected to be contained in the assigning model of the bond rating agencies. However, the ranges of bond ratings in existing studies vary from 5 to 20 and the prediction models were developed with samples in which the target companies and the observation periods are different. Thus, a simple comparison of the prediction accuracies in each study cannot determine the best prediction model. In order to conduct a fair comparison, this study has collected corporate bond ratings and financial characteristics from 2013 to 2017 and applied prediction models to them. In addition, we applied the elastic-net penalty for the linear regression, the ordered logit, and the ordered probit. Our comparison shows that data-driven variable selection using the elastic-net improves prediction accuracy in each corresponding model, and that the random forest is the most appropriate model in terms of prediction accuracy, which obtains 69.6% accuracy of the exact rating prediction on average from the 5-fold cross validation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.3
• /
• pp.1-17
• /
• 2018

Over the past five years (2010-2014), the total number of traffic accidents has decreased from 226,878 to 223,552 with decrease of 0.37 percent each year. The death toll has also decreased from 5,505 to 4,762. However, the number of rental car accidents and fatalities has been steadily increased. Despite of its growth, no previous study has been conducted on rental car accident severity. This study analyzed data of 18,050 rental car accidents in South Korea collected from 2010 to 2014 and then processed in order to identify which factors could affect the accident severity. Seventeen factors related to rental car accident severity were grouped into four categories: driver, vehicle, roadways and environment. As a result of the ordered probit model analysis, fourteen variables excluding age, intersection, and day of week were found to affect the severity of rental car accidents. The results of the study summarized as follows. First of all, violation of traffic regulations such as speeding increase the severity of rental car accidents. Secondly, rental accident severity is higher at curved sections of complicated roadway, which the driver's field of view is impaired. The results of this study can be used to reduce the severity of rental car accidents in transportation safety.

• Journal of Korean Society of Transportation
• /
• v.36 no.1
• /
• pp.13-22
• /
• 2018

Buses, one of the representative public transportation modes, are divided into a vareity of service types according to the purpose of operation, operating distance, and management agencies. Although bus-involved crashes may cause large amount of damage due to the higher number of passengers boarded on a bus, prior research has little focused on crash severity according to bus service types. This study aims to investigate factors influencing crash severity in bus-involved crashes and to present policy implications to reduce crash severity by bus service type. To do this, bus-involved crash data from the Traffic Accident Analysis System (TAAS) during five-year period are used. Ordered probit models for three types of bus service, i.e., city bus, suburban and express buses, and charter buses, are estimated to analyze the factors of accident severity. The results show that there are significant differences of factors affecting crash severity among the types of bus services while speed and road surface influence all the types of buses. In case of local buses, time of day, roadway alignment, and installation of a traffic signal are found to be statistically significant factors. Seat belt and road class have significant effects on injury severity of the intercity and express buses. Chartered buses have time of day, driving experience, seatbelt, traffic signal, and day of week as the significant factors. The results of this study are expected to contribute to the reduction of the crash severity by each bus service type.

• Journal of Labour Economics
• /
• v.27 no.2
• /
• pp.91-115
• /
• 2004

Based on household characteristics, this study analyzes the sources of changes in income class. Using KLI panel data in 1998 and 2001, household equivalent income is calculated and households whose income class is changed are identified. Various household characteristics are examined to understand which characteristics are influential in income class changes. Empirical estimations are carried out by employing an ordered probit model. Region of residence, age of household head, education level of the head, the number of employed family members in 1998, and a change in the number of employed family members are shown to be statistically significant. Calculation of marginal probability based on the ordered probit estimation results show that the probability of upward movement in income class decreases as a household lives in rural areas, while the probability of upward movement increases as the household's head is better educated, the number of employed family members are higher and there is a higher increase in the number of employed family members. Age of the head has mixed results; while the probability of upward movement in income class decreases as the head gets older for the households in middle and high income classes, that probability increases as the head is in the range of the 40s and the 50s in low income class households.

• Journal of Korean Society of Rural Planning
• /
• v.23 no.3
• /
• pp.53-60
• /
• 2017

In order to export Korean spray roses to the China, it is needed to analyse chinese preferences, rose attributes, and purchase intentions. The purpose of this study is to present the implications on the production and distribution of roses for export by analyzing the quality preference attributes and purchase intention of Korean rose for Chinese flower experts. A survey on the preference and purchase intention of Korean flower roses by Chinese flower experts was conducted through face - to - face interviews with flower show participants in China. Approximately 100 Chinese flower experts who participated in the Flower Show in 2016 received the questionnaire, and 86 survey results could be used for analysis. Survey data were analyzed using ordered probit and bivariate probit models. As a result of an analysis, it was found that Chinese flower experts were more likely to buy Korean roses than Chinese roses even if they consider flower color, leaf shape and size and color diversity. The probability of purchasing more than twice the price was higher than that of the color diversity considering the flower shape, leaf shape and size, but the bivariate order probit model was larger than that of flowers, leaves and size, and the order of probability size was changed. In order to increase the export of Korean spray roses to the Chinese market, We need to increase Chinese experts' preferences and satisfaction. For this purpose, it is very important to develop export varieties of roses with large flower buds and shape / coloring, and to apply the useful post-harvest technology that can extend freshness and distribution period of export roses.

• Journal of Korean Society of Transportation
• /
• v.31 no.6
• /
• pp.53-66
• /
• 2013

The major purpose of this study is to evaluate methodologies to predict the injury severity of pedestrian-vehicle collisions. Methodologies to be evaluated and compared in this study include Binary Logistic Regression(BLR), Ordered Probit Model(OPM), Support Vector Machine(SVM) and Decision Tree(DT) method. Valuable insights into applying methodologies to analyze the characteristics of pedestrian injury severity are derived. For the purpose of identifying causal factors affecting the injury severity, statistical approaches such as BLR and OPM are recommended. On the other hand, to achieve better prediction performance, heuristic approaches such as SVM and DT are recommended. It is expected that the outcome of this study would be useful in developing various countermeasures for enhancing pedestrian safety.

• Journal of the Korean Society of Safety
• /
• v.30 no.1
• /
• pp.94-103
• /
• 2015

This study analyzes the influence factors on elderly pedestrian accident. Elderly people are easy to be badly injured by car accidents compared to younger people. Therefore, various plans and measures are required to protect elderly pedestrian from accidents. However, pedestrian accidents studies only focused on microscopic factors such as attribute of driver, pedestrian, road design. In order to prevent pedestrian accident and reduce the severity of the accident, not only microscopic factors but macroscopic variables such as urban planning and facility should be considered. In this regard, this study develops an ordered probit model introduced the characteristics of urban facility which were not considered in the previous studies. The result shows that there is higher level of accident severity in such areas as large commercial area, well-developed area with transportation infrastructure service and non-pedestrian safety zone. Thus, various and appropriate countermeasures should be prepared in order that pedestrian accident can be prevented in the areas mentioned above. In addition to the aforementioned variables, it is revealed that other variables including vehicle speed, gender and age of pedestrian, weather condition, type of vehicle, etc. partly affect the severity of pedestrian accident.

• Journal of Korean Society of Transportation
• /
• v.28 no.3
• /
• pp.75-84
• /
• 2010

South Korea is seeking for a solution to the problems of traffic congestion and environment: the increase of bicycle use. However many people feel that using a bicycle is inconvenient. Therefore, we developed bicycle level of service model from the user's perspective so that the existing bicycle roads can be evaluated and improved. The purpose of this paper is to develop a bicycle level of service (LOS) model by considering user's satisfaction and multiple factors that affect bicycle LOS. Bicycle LOS criteria is estimated by applying an ordered probit model, which is suitable for research relating to choice. In addition, we determine the bicycle LOS using three-level(A-C) LOS structure from the user position considering the satisfaction level that people can distinguish clearly. The results show that the bicycle LOS is largely determined by the bicycle road width. Other factors are involved as well, including bicycle road type, the number of access and egress point on the bicycle road corridor, pedestrian volume, and frequency of meetings.

• Journal of the Korean Society of Safety
• /
• v.32 no.6
• /
• pp.143-149
• /
• 2017

According to traffic accidents statistics, the number of fatalities, injuries and the rate of increase of traffic accidents have been decreasing over last 5-years. The fatality rate is 1.9 for total accidents but the fatality rate for single vehicle accidents shows a 7.9, which is 4 times greater than the average for all accidents. Single vehicle accidents, usually occur as a vehicle impacts a fixed objects on the roadside as the vehicle runs-off from the road. However, few researches have been conducted considering the accident severity of single vehicle accidents which impact to the fixed objects on the road. The single vehicle accident is directly related to the composition of road cross section, (since it is the required the minimum width of a road for all run-off-the-road vehicles to recover or come to a safe stop). Therefore, this study analyzes the influence of road cross section on traffic accidents to find out the severity of single vehicle accident. To analyze the road elements which are related to the accident severity, the Ordered Probit Model was used. As variables, the element of road cross section such as the radius(m), vertical curve(%), cross sectional grade(%), road width(m). number of climbing lane, median, and curb, were used (as was the 3-years of accidents data). This study found out that cross slope(%), road width(m), and the number of climbing lane are related to the severity of accident. The result of this study could be expected to improve the road safety and to be used as the base data for further road safety research.

• Journal of Korean Society of Transportation
• /
• v.26 no.5
• /
• pp.101-115
• /
• 2008

This study reports UTIS(Urban Traffic Information System), which has been generalized in developed countries through brisk research and development and is being promoted for introduction by National Police Agency and Road Traffic Authority to reduce the astronomical amount of social expenses including traffic congestion expenses. Also this study investigates the proper charges for using by the preestimate of demand and contentment according to methods of payment after the service is introduced. The results of this study are as follows. First, demand forecast model is constructed by Binary Logit Model. Second, forecast models of using aspects of UTIS service according to methods of payment are established by Ordered Probit Model. Third, the proper charges for using of UTIS service according to methods of payment are presented to the supplier in the aspects of users. For this, preferences by using aspects and methods of payment are captured. And unit elasticity of coefficient of utilization is understood through responsiveness analysis according to methods of payment.