• The Korean Journal of Applied Statistics
• /
• v.33 no.1
• /
• pp.47-59
• /
• 2020

In this paper, we present the longitudinal Markov binary regression model with t-link function when its transition order is known or unknown. It is assumed that logit or probit models are considered in binary regression models. Here, t-link function can be used for more flexibility instead of the probit model since the t distribution approaches to normal distribution as the degree of freedom goes to infinity. A Markov regression model is considered because of the longitudinal data of each individual data set. We propose Bayesian method to determine the transition order of Markov regression model. In particular, we use the deviance information criterion (DIC) (Spiegelhalter et al., 2002) of possible models in order to determine the transition order of the Markov binary regression model if the transition order is known; however, we compute and compare their posterior probabilities if unknown. In order to overcome the complicated Bayesian computation, our proposed model is reconstructed by the ideas of Albert and Chib (1993), Kuo and Mallick (1998), and Erkanli et al. (2001). Our proposed method is applied to the simulated data and real data examined by Sommer et al. (1984). Markov chain Monte Carlo methods to determine the optimal model are used assuming that the transition order of the Markov regression model are known or unknown. Gelman and Rubin's method (1992) is also employed to check the convergence of the Metropolis Hastings algorithm.

• Asia Pacific Journal of Business Review
• /
• v.5 no.2
• /
• pp.19-44
• /
• 2021

Sub Saharan Africa (SSA) is receiving increased investments in the energy sector under the belt and road initiative (BRI) project since its inception in 2013. SSA has a worse energy efficiency ratio coupled with deficient electricity access, through analysis showed varied impacts on the SSA countries due to the BRI initiative. This study dilves into the influencing factors for Energy Efficiency (EE) in 38 SSA countries, applying the probit and logit approach for 2000-2018. The Multiple-regression model shows significant results of some variables such as foreign direct investment, gross domestic product, and port infrastructure quality being significant on EE under BRI initiative countries. However, the logit and probit models produce similar results and the marginal effect for the entire variable, except energy imports that do not likely impact EE. Furthermore, the interaction of quality of port infrastructure and foreign direct investment variables produces significant results, highlighting the increased investments SSA receives under the BRI initiative in the energy and transport sectors. The model Percent correctly predicted (PCP) value was about 84%, indicating it correctly classified the variables and about 16% not classified. The study recommends EE performance standards should be incorporated on energy projects in SSA to ensure that these projects are energy efficient and decouple SSA's energy demand from economic growth. The research proffers suggestions for policy regarding the BRI initiative in SSA and the implications on sustainable energy and building a community with a shared future.

• International Journal of Highway Engineering
• /
• v.18 no.6
• /
• pp.173-180
• /
• 2016

OBJECTIVES : Fixed roadside objects are a threat to drivers when their vehicles deviate from the road. Therefore, such roadside objects need to be suitably dealt with to decrease accidents. This study determines the factors affecting the severity of accidents because of fixed roadside objects. METHODS : This study analyzed the crash severity impact of fixed roadside objects by using ordered probit regression as the analysis methodology. In this research, data from 896 traffic accidents reported in the last three years were used. These accidents consisted of sole-car accidents, fixed roadside object accidents, and lane-departure accidents on the national highway of Korea. The accident severity was classified as light injury, severe injury, and death. The factors relating to the road and the driver were collected as independent variables. RESULTS : The result of the analysis showed that the variables of the crash severity impact are the collision location (left side), gender of the driver (female), alcohol use, collision facility (roadside trees, traffic signals, telephone poles), and type of road (rural segments). Additionally, the collision location (left side), gender of the driver (female), alcohol use, collision facility (street trees, traffic signals, telephone poles), and type of road (rural segments), in order of influence, were found to be the factors affecting the crash severity in accidents due to fixed roadside objects. CONCLUSIONS : An alternative solution is urgently required to reduce the crash severity in accidents due to fixed roadside objects. Such a solution can consider the appropriate places to install breakaway devices and energy-absorbing systems.

• Korea journal of population studies
• /
• v.26 no.2
• /
• pp.91-110
• /
• 2003

This study analyzed data from 1997 Korea's Behavioral Risk Factor Surveillance System Survey collected through telephone questionings based on the multi-stage stratified random sampling. We categorized respondents into those who had ever drunk an alcoholic beverage in the last month and those who didn't and, referring to the World Health Organization's guideline, the former group were further categorized into low risk drinking group and high risk drinking group. Employing bivariate probit regression analyses with censoring on independent variables such as preferred type of alcoholic beverage, the number of types of beverages consumed, age, marital status, education, occupation, residential area, current smoking, body mass index and stress suggested (1) that those who prefer soju are more likely to involve high risk drinking than those who and prefer the other alcoholic beverages (2) that those who are relatively older, who live without a partner, who have jobs, who. are vulnerable to stress, or who enjoy more than one type of beverage are more likely to be exposed to high risk drinking than the others.

• 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.

• 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 Asian Finance, Economics and Business
• /
• v.7 no.9
• /
• pp.229-239
• /
• 2020

This paper examines the impact of gender on access to debt finance among Vietnamese enterprises. The paper investigates data and variables retrieved from the World Bank Enterprise Survey dataset using five Probit models. The regression results suggest that there exist more unfavourable debt financing conditions for women-led firms (WLF), measured as a lower probability of having loan applications fully approved. Firm's age, working sector, and perception of access to finance as a difficulty are found to have explanatory power on the discrimination. More importantly, the perception of debt finance as a difficulty or firms' level of confidence significantly explains the variance of the dependent variable of probability of loan approval, or gender effect would be more pronounced if the firm already has a low level of confidence. The paper also contributes in testing for the gender effect on Vietnamese enterprises from different sectors and scale, unlike other prior research papers focusing on specific sectors and/or small and medium enterprises only. The findings are highly useful for Vietnamese credit institutions to set out a specific business policy to attract more WLFs and help promoting gender equality in the working environment, especially in debt financing, which is often neglected in existing regulation and policy frameworks.

• Journal of Information Technology Applications and Management
• /
• v.27 no.3
• /
• pp.37-54
• /
• 2020

In response to the recent decline in the school-age population, universities have made attracting foreign students a major policy task for universities. As a result, the number of foreign students increased rapidly in terms of quantity, but in terms of quality, the risk is inevitable. Accordingly, the government presented education and internationalization competency certification system indicators on the basis of which quality control of students was systematized. Based on the above certification system, this study focused on analyzing the multiple factors that are actually given to the academic adaptation (performance) of the 2200 students who entered a certain university. In addition, factors other than the certification system index were discovered to comprehensively track how they affect the academic performance of students studying abroad. The researcher found the multi-reciprocal model analysis showed that the difference between the learner and the moderator was significant, and whether or not they had the Korean proficiency test (TOPIK) was significant. It also said that it could have a direct impact on Chinese University Entrance Exams (高考) are significant. If a model that is very effective in selecting students is established by each university and used as an indicator through this study, it will serve as a basis for efficient selection of students.

• Communications for Statistical Applications and Methods
• /
• v.26 no.3
• /
• pp.315-323
• /
• 2019

Panel data sets have recently been developed in various areas, and many recent studies have analyzed panel, or longitudinal data sets. Often a dichotomous dependent variable occur in survival analysis, biomedical and epidemiological studies that is analyzed by a generalized linear mixed effects model (GLMM). The most common estimation method for the binary panel data may be the maximum likelihood (ML). Many statistical packages provide ML estimates; however, the estimates are computed from numerically approximated likelihood function. For instance, R packages, pglm (Croissant, 2017) approximate the likelihood function by the Gauss-Hermite quadratures, while Rchoice (Sarrias, Journal of Statistical Software, 74, 1-31, 2016) use a Monte Carlo integration method for the approximation. As a result, it can be observed that different packages give different results because of different numerical computation methods. In this note, we discuss the pros and cons of numerical methods compared with the exact computation method.

• International Journal of Highway Engineering
• /
• v.10 no.3
• /
• pp.47-56
• /
• 2008

Generally, accident exposure at intersections is relatively higher than that at roadway segments due to more possibility of merging, diverging, turning, crossing, and weaving maneuver. Furthermore, the traffic accident rate at intersections has been rapidly increasing since 1990's. Since there is more opportunity of conflict at unsignalized intersection, frequency and severity of traffic accident are more severe than signalized intersections. The purpose of the study is to analyze factors causing vehicle crashes and provide intersection design guidelines to improve intersection safety. For this study, vehicle to vehicle crash data of 116 rural 3 legs unsignalized were collected and field surveys were conducted for traffic and geometric conditions. Ordered probit models were developed to analyze the severity of crashes. It was found that weather, obstacles in minor roadsides, presence of major exclusive right lane, presence of major road crosswalk, difference between posted speed of major road and minor road, land-use around intersections, shoulder width of major road, ADT of major road are significant factors for intersection safety.