• Economic Analysis
• /
• v.26 no.4
• /
• pp.39-64
• /
• 2020

Typical business cycle models have difficulties in explaining key macroeconomic labor market variables, such as employment and unemployment, as they usually consider labor hour choices only. In this paper, we introduce labor market search and matching frictions into a New Keynesian nominal rigidity model and estimate it by Bayesian methods to examine the dynamics of the key labor market variables and business cycles in Korea. The results show that unemployment rates are largely explained by technology shocks, which affect the labor demand side, as well as labor supply shocks. In addition, wage bargaining shocks originating from the bargaining process between firms and workers have non-negligible negative effects on output and employment growth, and careful measures need to be taken to limit their adverse effects.

• Journal of Labour Economics
• /
• v.35 no.2
• /
• pp.117-146
• /
• 2012

This study demonstrates the gender difference in the factors that affect job changes and the resulting wage changes in the recent Korean labor market. By using the KEAPS (2003-2007), we found that male workers uniquely tend to stay longer at their current jobs when they have families to support. After controlling self-selection bias, we also found that wage changes resulting from switching jobs differ between male and female workers during this studied period.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.11a
• /
• pp.361-364
• /
• 2005

본 논문에서는 순서 통계량을 이용한 유한 고장 NHPP 모형들이 제안되었다. 이 모형들은 결함당 고장발생률이 단조 증가하거나 단조 감소하는 패턴을 가진다. 그리고 수명 분포에서는 기존의 모형들과 비교하고 kappa(2) 분포를 이용한 소프트웨어 신뢰성 모형을 제안하여 이 모형의 특성과 효율성에 대하여 제시하였다. 고장 간격 시간 자료를 이용한 무한고장 NHPP 모형들에 대한 모수 추정은 최우 추정법을 사용하였고 적용 분포들의 적용을 용이하게 하기 위하여 특수한 형태를 제시하였다. 실제고장 자료를 이용한 자료분석에서는 편차자승합을 이용한 모형 선택과 적합도 및 치우침 검정을 실시하여 그 결과를 나열 하였다.

• Korea journal of population studies
• /
• v.29 no.2
• /
• pp.27-51
• /
• 2006

In this paper, I have tested various kinds of methods for mortality projection and chose Lee-Carter method for projection of Korean mortality by age and sex. I reviewed the trends of life tables and life expectancies by age and sex from 2005 to 2050 projected by Lee-Carter method and found that the method was very applicable for Korean mortality projection. The differences between reported and estimated data for the period of 1971-2003 were small enough for both sexes and for all of the age groups. The projected life expectancies in 2051 were 82.73 years for males and 89.41 for females, and the differences decreased from 7.06 years in 2005 to 6.68 years. Because of the limitation of Korean infant mortality rate, I adopted the Japanese estimated IMR in 2050 as Korean object level in 2051. When the time series of IMR become long enough, we can use Korean IMR directly for the mortality projection. In addition, if we can estimate the changes of the main cause of death correctly in future, the mortality projection will be more correct and reliable. This will be available when we can produce a long series of life tables by cause of deaths.

• Journal of Korean Society of Transportation
• /
• v.28 no.1
• /
• pp.77-86
• /
• 2010

The study developed physical distribution channel choice models reflecting decision making of the firms and studied how choice decision factors influence selection of distribution channel. The distribution channel survey data in Korea was used to do empirical study. As a choice set, distribution channels were classified into two main choice channels: direct and indirect channels. In addition, indirect channels were classified into other three channels according to the type of intermediate point: distribution center, wholesale store, and agency. This study developed choice models by applying both binary and multinomial logit model with various set of factors. The results showed that the developed logit models seemingly reflect distribution channel choice behaviors. The hypothesis tests on how each factor influences choice of distribution channel were performed and discussed as well.

• Journal of Digital Convergence
• /
• v.19 no.2
• /
• pp.61-69
• /
• 2021

The military pension deficit is increasing due to an increase in the average life expectancy and pension option rate, and a significant reason for this is estimated to be a continued increase in the number of military pension recipients. In terms of the soundness of military pension finances, this paper uses the Markov chain model to validate the stability of the military group, suggesting the direction of future military pension system in terms of the ratio of pension receipts to employees, and verifying the feasibility of the method applied through verification. Through this paper, we have confirmed that the initial 45,270 military personnel converge to 43,141 after a certain period of time and reach a stable state, which is expected to help us to estimate the long term size of military pension recipients to confirm the direction of national financial support. Military man who are eligible for pensions for more than 20 years have a relatively low rate of turnover or retirement compared to ordinary private groups, making it easier to define their status and simplify state transition probabilities. Therefore, it is expected that the sustainability of the military pension will be confirmed from a long term perspective by viewing the military group as a system and applying it to the Markov chain model by checking the probability of transfer of status such as promotion, maintaining the current grade, and retirement during the period.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.2
• /
• pp.543-551
• /
• 1999

The primary purposes in this paper are to analyze the class separation of features in handwritten numeral recognition and to make use of the results in feature selection. Using the Parzen window technique, we compute the class distributions and define the class separation to be the overlapping distance of two class distributions. The dimension of a feature vector is reduced by removing the void or redundant feature cells based on the class separation information. The experiments have been performed on the CENPARMI handwritten numeral database, and partial classification and full classification have been tested. The results show that the class separation is very effective for the feature selection in the 10-class handwritten numeral recognition problem since we could reduce the dimension of the original 256-dimensional feature vector by 22%.

• Journal of Environmental Policy
• /
• v.14 no.1
• /
• pp.3-32
• /
• 2015

The critical temperature and the rate of increase in excess death caused by heat waves in the age group of 65 years and older are derived. The value of statistical life method was used to quantify economic damages, and the willingness to pay after 71 years of age for 10 years was measured based on the dichotomous choice contingent valuation method survey. The result shows about KRW 481,110,000 is required annually to reduce the possibility of death by climate change to 1/1000.

• Korean Journal of Cognitive Science
• /
• v.19 no.4
• /
• pp.459-476
• /
• 2008

The user needs to find the answer to your question is growing fast at the service using collective intelligent knowledge. In the previous researches, it was proven that the non-text information like view counting, referrer number, and number of answer is good in evaluating answers. There were also many works about evaluating answers using the various kinds of word dictionaries. In this work, we propose new method to evaluate answers to question effectively using user reputation that estimated by the social activity. We use a modified PageRank algorithm for estimating user reputation. We also use the similarity between question and answer. From the result of experiment in the Naver GisikiN corpus, we can see that the proposed method gives meaningful performance to complement the answer selection rate.

• Journal of Internet Computing and Services
• /
• v.3 no.6
• /
• pp.43-51
• /
• 2002

In this paper, we study the new packet dropping scheme using an active queue management algorithm. Active queue management mechanisms differ from the traditional drop tail mechanism in that in a drop tail queue packets are dropped when the buffer overflows, while in active queue management mechanisms, packets may be dropped early before congestion occurs, However, it still incurs high packet loss ratio when the buffer size is not large enough, By detecting congestion and notifying only a randomly selected fraction of connection, RED causes to the global synchronization and fairness problem. And also, it is the biggest problem that the network traffic characteristics need to be known in order to find the optimum average queue length, We propose a new efficient packet dropping method based on the active queue management for congestion control. The proposed scheme uses the per-flow rate and fair share rate estimates. To this end, we present the estimation algorithm to compute the flow arrival rate and the link fair rate, We shows the proposed method improves the network performance because the traffic generated can not cause rapid fluctuations in queue lengths which result in packet loss