• 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.

• The International Journal of Costume Culture
• /
• v.2 no.1
• /
• pp.31-42
• /
• 1999

The category killer that has been rapidly growing mainly in advanced countries since early 1990's, is a mew distribution model which aims for obtaining market controlling power by surpassing competing businesses in a specific area of products. The domestic situation of category killers is very different from that of advanced ones abroad since it has just been introduced into the Korean market. At the moment, there are only 10 or so companies operating in the market : Geopyung's , Taeheng's , Midopa's , of Sinsegye Department store, adn of Yerim International. The purpose of this study is to examine problems of domestic companies in the present market by analysing the operation status of category killers in domestic markets as well as foreign ones, and to suggest a counter-strategy of category killers for the distribution environment of the 21st century to improve the competitiveness of Korean distribution industry. The competitiveness of category killers lies above all in products lines. Category killers are equipped with the greatest number of products lines among those of competing businesses due to maximized product selections in an limited range. Another source of competitiveness may be found in balanced strategy positioning. That is to say, category killers are in a position where they can adjust policies towards any of the three purposes while aiming at them altogether : prices of discount stores, products range of specialty stores, and customer service level of department stores. It is also necessary for efficient store operation to use information technology such as electronic data interchange (EDI), electronic pose system(EPOS) and electronic funds transfer (EFTPOS). As for the cost structure, category killers can gain an advantage over other business since operating cost of various sections can be saved. There are, however, certain risks that category killers with strong competitiveness may influence on other businesses a great deal and even facilitate their decline. Yet it seems that the growth of category killers will be more viciously restrained by continuous challenges from other businesses. The distribution industry is supposed to develop through such competition and restraint.

• Communications for Statistical Applications and Methods
• /
• v.25 no.3
• /
• pp.245-261
• /
• 2018

Attempts have been made to define new classes of distributions that provide more flexibility for modelling skewed data in practice. In this work we define a new extension of the generalized gamma distribution (Stacy, The Annals of Mathematical Statistics, 33, 1187-1192, 1962) for Marshall-Olkin generalized gamma (MOGG) distribution, based on the generator pioneered by Marshall and Olkin (Biometrika, 84, 641-652, 1997). This new lifetime model is very flexible including twenty one special models. The main advantage of the new family relies on the fact that practitioners will have a quite flexible distribution to fit real data from several fields, such as engineering, hydrology and survival analysis. Further, we also define a MOGG mixture model, a modification of the MOGG distribution for analyzing lifetime data in presence of cure fraction. This proposed model can be seen as a model of competing causes, where the parameter associated with the Marshall-Olkin distribution controls the activation mechanism of the latent risks (Cooner et al., Statistical Methods in Medical Research, 15, 307-324, 2006). The asymptotic properties of the maximum likelihood estimation approach of the parameters of the model are evaluated by means of simulation studies. The proposed distribution is fitted to two real data sets, one arising from measuring the strength of fibers and the other on melanoma data.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2007.11a
• /
• pp.652-655
• /
• 2007

Due to stagnation of domestic market, increasing number of domestic construction companies started to make inroads into foreign market recently. Yet compared to domestic market, there are much more risks in the foreign market which companies may confront. So deliberate and rational decision making skills are required. Accordingly, there has been many researches which analyzed the risk of individual markets and also studies covering decision support models. In this study, we suggest a model concerning financial issues when branching out into a new market, specially in the construction companies' point of view. For this we used a real options game which shows real competition status of a new market and deduced a feature of that market, Upon these results, we also suggest a model which helps firms to decide whether investing in the expansion is smart action or not. The model developed in this study is made in specific circumstances of limited conditions. The future study makes more realistic models considering subjects like disproportion in information and generalization of competing companies.

• Journal of Labour Economics
• /
• v.24 no.1
• /
• pp.207-230
• /
• 2001

This paper uses the Korean Labor Panel data to investigate changes in the employment types of male workers following their job changes with the classification of workers into three categories: regular wage workers, non-regular wage workers, and self-employed workers. It also estimates a competing-risks hazard model to analyze the determinants of employment types of workers. The results show that the type of employment of a worker at an immediate previous job has a critical importance in determining his employment type at a new job and that the types of employment at jobs other than the immediate previous job also play some role in determining the type of employment at a new job, although their impact declines as the number of intervening jobs increases. A job loser, who worked as a non-regular worker at his immediate previous job, for example, is considerably less likely to find a regular job, but more likely to get reemployed at another non-regular job than one who worked as a regular worker at his immediate previous job. Similarly, a worker who quit self-employment is much less likely to find a regular job but more likely to restart his own business than one who worked as a regular worker at his immediate previous job. These findings suggest that it is not easy at all for a worker who worked as either a non-regular worker or self-employed worker to become a regular worker, although it might be premature to assert that non-regular jobs or self-employed jobs are dead-end jobs. Another interesting finding of this analysis is that a high unemployment rate lowers a probability of reemployment at either regular jobs or self-employed jobs, but raises a non-regular job reemployment probability, which strongly implies that as labor market conditions become adverse to workers the proportion of non-regular employment can rise rapidly.

• Korean Journal of Radiology
• /
• v.22 no.12
• /
• pp.1985-1995
• /
• 2021

Objective: Although the liver-to-spleen volume ratio (LSVR) based on CT reflects portal hypertension, its prognostic role in cirrhotic patients has not been proven. We evaluated the utility of LSVR, automatically measured from CT images using a deep learning algorithm, as a predictor of hepatic decompensation and transplantation-free survival in patients with hepatitis B viral (HBV)-compensated cirrhosis. Materials and Methods: A deep learning algorithm was used to measure the LSVR in a cohort of 1027 consecutive patients (mean age, 50.5 years; 675 male and 352 female) with HBV-compensated cirrhosis who underwent liver CT (2007-2010). Associations of LSVR with hepatic decompensation and transplantation-free survival were evaluated using multivariable Cox proportional hazards and competing risk analyses, accounting for either the Child-Pugh score (CPS) or Model for End Stage Liver Disease (MELD) score and other variables. The risk of the liver-related events was estimated using Kaplan-Meier analysis and the Aalen-Johansen estimator. Results: After adjustment for either CPS or MELD and other variables, LSVR was identified as a significant independent predictor of hepatic decompensation (hazard ratio for LSVR increase by 1, 0.71 and 0.68 for CPS and MELD models, respectively; p < 0.001) and transplantation-free survival (hazard ratio for LSVR increase by 1, 0.8 and 0.77, respectively; p < 0.001). Patients with an LSVR of < 2.9 (n = 381) had significantly higher 3-year risks of hepatic decompensation (16.7% vs. 2.5%, p < 0.001) and liver-related death or transplantation (10.0% vs. 1.1%, p < 0.001) than those with an LSVR ≥ 2.9 (n = 646). When patients were stratified according to CPS (Child-Pugh A vs. B-C) and MELD (< 10 vs. ≥ 10), an LSVR of < 2.9 was still associated with a higher risk of liver-related events than an LSVR of ≥ 2.9 for all Child-Pugh (p ≤ 0.045) and MELD (p ≤ 0.009) stratifications. Conclusion: The LSVR measured on CT can predict hepatic decompensation and transplantation-free survival in patients with HBV-compensated cirrhosis.