• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.6
• /
• pp.324-333
• /
• 2018

The aim of this study was to investigate the latent classes and predictors of chronic diseases such as hypertension, dyslipidemia, arthritis, thyroid disease, depression, atopy, allergy, and diabetes. The subjects of this study were Korean citizens who participated in the Korea National Health and Nutrition Examination Survey in 2014. Stratified cluster sampling method was used with a sample size of 7,550. Latent hierarchy analysis was applied to this data. Four classes were identified. Class 1 consisted of participants with hypertension and diabetes. Class 2 consisted of participants with atopy and allergies. Class 3 consisted of participants with dyslipidemia, arthritis, thyroid disease, and depression. Class 4 consisted of participants without any chronic diseases. In comparing Class 1 to Class 4, age, physical activity, self-management, obesity, and presence of high cholesterol were found to be significant. In comparing Class 2 to Class 4, gender, age, and education level were significant. When Class 3 was compared to Class 4, gender, age, pain and discomfort, as well as high cholesterol were found to be significant. Diabetes and hypertension should be treated as comorbid conditions, applying integrated treatments involving effective drug treatment, diet, and physical activity programs. Atopy was found to be strongly correlated with allergies. Thyroid disease was found to coexist with dyslipidemia and arthritis, along with having a strong correlation to depression. Age-appropriate preventive measures can help reduce the risk of chronic diseases.

• The Korean Journal of Applied Statistics
• /
• v.37 no.2
• /
• pp.225-237
• /
• 2024

In the analysis of competing risks data, some of covariates may not be fully observed for some subjects. In such cases, excluding subjects with missing covariate values from the analysis may result in biased estimates and loss of efficiency. In this paper, we studied multiple imputation and the augmented inverse probability weighting method for regression parameter estimation in the cause-specific proportional hazards model with missing covariates. The performance of estimators obtained from multiple imputation and the augmented inverse probability weighting method is evaluated by simulation studies, which show that those methods perform well. Multiple imputation and the augmented inverse probability weighting method were applied to investigate significant risk factors for the risk of death from breast cancer and from other causes for breast cancer data with missing values for tumor size obtained from the Prostate, Lung, Colorectal, and Ovarian Cancer Screen Trial Study. Under the cause-specific proportional hazards model, the methods show that race, marital status, stage, grade, and tumor size are significant risk factors for breast cancer mortality, and stage has the greatest effect on increasing the risk of breast cancer death. Age at diagnosis and tumor size have significant effects on increasing the risk of other-cause death.

• Journal of the Korean Regional Science Association
• /
• v.33 no.3
• /
• pp.61-78
• /
• 2017

Among several policies for industrial decentralization introduced since the 1960s, business relocation grant policies put a heavy financial burden on central and local governments. This study investigates the change in the likelihood of manufacturing establishments' relocation to the non-SMA associate with the change in business relocation grant policies. Using the mining and manufacturing survey data from 1996 to 2014, manufacturing firms' relocation decision model in nested logit structure was estimated. The data showed that the proportion of movements from the SMA to the non-SMA significantly increased after the introduction of the grant policies. However, estimation results of firms' relocation decision model indicated that the likelihood of firms relocating from the SMA to the non-SMA decreased after the introduction of the grant policies. In particular, firms' likelihood to move into the rural regions is even lower in the period of the grant extension. This suggests that increasing rate of relocations toward the rural regions may have been driven by the growing advantage of rural locations, such as low land rent and improvement in market accessibility, rather than the grants per se. This implies that the alleviation of physical and environmental constraints of the rural regions and the creation of business friendly environment such as easy access to premises at reasonable prices and strengthened linkage with the SMA, rather than simple provision of business relocation grants, needed to attract businesses in the rural regions.

• The Korean Journal of Applied Statistics
• /
• v.15 no.1
• /
• pp.73-84
• /
• 2002

Linear regression models with inequality constraints on the coefficients are frequently used in economic models due to sign or order constraints on the coefficients. In this paper, we propose a Bayesian approach to selecting significant explanatory variables in linear regression models with inequality constraints on the coefficients. Bayesian variable selection requires computation of posterior probability of each candidate model. We propose a method which computes all the necessary posterior model probabilities simultaneously. In specific, we obtain posterior samples form the most general model via Gibbs sampling algorithm (Gelfand and Smith, 1990) and compute the posterior probabilities by using the samples. A real example is given to illustrate the method.

• Journal of Korea Port Economic Association
• /
• v.39 no.2
• /
• pp.97-110
• /
• 2023

This study examines the effect of macroeconomic shocks on the financial stability of the Korean shipping industry. Using Firth logistic regression model, this study estimates the default probability of a shipping company. The results from a default prediction model suggest that total assets are negatively correlated with default probability, while total debt is positively correlated with default probability. Based on the results from a default prediction model, this study investigates the effect of macroeconomic shocks, namely total assets, sales, and total debt shocks, on a shipping company's default probability. The stress test results indicate that a decrease in sales and total assets significantly deteriorates the financial stability of a shipping company.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.31 no.3
• /
• pp.115-128
• /
• 2019

In this study, a probabilistic model for the estimation of yearly workable wave condition period for offshore operations is developed. In doing so, we first hindcast the significant wave heights and peak periods off the Ulsan every hour from 2003.1.1 to 2017.12.31 based on the meteorological data by JMA (Japan Meterological Agency) and NOAA (National Oceanic and Atmospheric Administration), and SWAN. Then, we proceed to derive the long term significant wave height distribution from the simulated time series using a least square method. It was shown that the agreements are more remarkable in the distribution in line with the Modified Glukhovskiy Distribution than in the three parameters Weibull distribution which has been preferred in the literature. In an effort to develop a more comprehensive probabilistic model for the estimation of yearly workable wave condition period for offshore operations, wave height distribution over the 15 years with individual waves occurring within the unit simulation period (1 hour) being fully taken into account is also derived based on the Borgman Convolution Integral. It is shown that the coefficients of the Modified Glukhovskiy distribution are $A_p=15.92$, $H_p=4.374m$, ${\kappa}_p=1.824$, and the yearly workable wave condition period for offshore work is estimated to be 319 days when a threshold wave height for offshore work is $H_S=1.5m$. In search of a way to validate the probabilistic model derived in this study, we also carry out the wave by wave analysis of the entire time series of numerically simulated significant wave heights over the 15 years to collect every duration periods of waves the height of which are surpassing the threshold height which has been reported to be $H_S=1.5m$ in the field practice in South Korea. It turns out that the average duration period is 45.5 days from 2003 to 2017, which is very close to 46 days from the probabilistic model derived in this study.

• Journal of Labour Economics
• /
• v.26 no.1
• /
• pp.111-151
• /
• 2003

This study attempted to analize the hazard rate from unemployment and the influncing factors on the rate by regions. The data this study uses is Korea Labor Institute Panal Study(1998-2001) and the models are hazard analysis and Cox model. The results of hazard analysis are as follow. In capital and it's vicinity, the duration of unemployment is shorter than other regions even if the unemployment rate is higher. The labor market segmentation is confirmed between capital and it's vicinity region and other regions. Kyungsang region is higher in the unemployment hazard rate than Chunla or Chungchung regions. The duration of unemployment in capital and it's vicinity is 9.29 months comparing 11.86 months in the other region. The difference is statistically significant by the significance level 0.001. The duration of unemployment in Kyungsang is 6.96 months comparing 10.95 months in Chunla region. The Cox results which indicate the influncing factors on the hazard rate are as follow. In the regions like non-metro cities and non-capital and vicinitiy, the factors such as female, tenure, wage earners, manufacturing, wholesale and retale decrease the hazard rate. The results indicate that active labor market policies region by region are needed in Korea, especially for the marginal unemployed workes from non flourishing sectors.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.2
• /
• pp.660-671
• /
• 2017

Drawing from the Korean Child and Youth Panel Survey (KCYPS), this study examined the changes in romantic relationship engagement among Korean adolescents across the country over a three-year period and the effects of the individual, familial, and school characteristics on the experience. Panel logit analysis showed that Korean adolescents were more likely to be engaged in a romantic relationship as they became older. Male adolescents were more likely than their female counterparts to have a romantic partner. The higher scores of self-esteem increased the likelihood of adolescents to be in a romantic relationship. On the other hand, having an opposite-sex sibling, the level of parental warmth, and annual household income did not have a significant relationship with the chance of romantic relationship engagement. On the contrary, all school-related variables were statistically related to the odds of being in a romantic relationship. Going to a sex-mixed school increased the odds, whereas academic adjustment and conformity to school rules decreased the likelihood. In addition, the positive relationships with schoolmates and teachers were associated with a higher chance of having a romantic partner. Based on these findings, the implications, limitations, and future research directions were also suggested.

• Korea Real Estate Review
• /
• v.27 no.3
• /
• pp.103-118
• /
• 2017

Under the ownership pre-sale system in the South Korean apartment market, developers can sell apartment ownerships as soon as they start to construct an apartment complex. In the South Korean apartment market, people call this kind of ownership "Bun-yang right." There is a time difference between ownership sale and apartment completion under the ownership pre-sale system. The pre-completion apartment ownerships can be resold to third parties until the apartment complexes are completed, which is called "Geon-mae" of the Bun-yang right. Using survival analysis, this research analyzed the elapsed time between ownership purchase and resale to a third party using 48,316 apartment units nationwide in the 192 complexes supplied from 2000 to 2016. Specifically, this study analyzed the influence of the real estate policy, contract term, location, apartment complex, and unit characteristics on the elapsed time between ownership purchase and resale to a third party. The empirical analysis revealed that the real estate policy and contract term characteristics have a significant effect on the elapsed time between ownership purchase and resale to a third party. Also, this study confirmed that the product characteristics, such as the location and apartment complex and unit characteristics, have an influence on the elapsed time between ownership purchase and resale to a third party.

• Communications for Statistical Applications and Methods
• /
• v.18 no.3
• /
• pp.287-294
• /
• 2011

Peer assessment is an educational valuation system that involves studying with a colleague and granting value to the progress made by the colleague. Although this method has many merits, there is also a drawback pertaining to calculating the mean of the scores that were granted to the levels of contribution. However, this has been improved upon by a diversified study. However, the concept of the chi-square test and p-value used in the preceding study is not easy individuals engaged in the industrial engineering field or education when using peer assessment. This study uses simple statistics like standard deviation, in addition to, investigating the availability of a suggested method as well as examples of utility and application. This study can contribute to increase the convenience of users through the use of convenience analysis and with this method.