• Management & Information Systems Review
• /
• v.29 no.4
• /
• pp.207-223
• /
• 2010

One of the important prudential regulations is the capital regulation. The current domestic and international capital regulation sets the minimum capital requirement according to the size of risk which is the simple sum of market risk and credit risk. However the portfolio theory suggests that, due to the effect of diversification, the total risk is less than the summation of market and credit risk. This paper investigates and does empirical test to verify the diversification effect in measuring financial firm's integrated risk. We verify the diversification effect between the market risk and credit risk. This paper's contribution is to present the empirical evidence that, considering the relationship between market and credit risk, the integrated risk is less than sum of them. This implication is that the surplus capital may be used for the other purposes, therefore enhancing capital allocation efficiency in view of society as a whole.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.9
• /
• pp.5585-5593
• /
• 2014

This study tested the hypothesis that the significance of the heterogeneous dispersion parameter in safety performance function (SPF) used to estimate the expected crashes is affected by the endogenous heterogeneous prior distributions, and analyzed the impacts of the mis-specified dispersion parameter on the evaluation results for traffic safety countermeasures. In particular, this study simulated the Poisson means based on the heterogeneous dispersion parameters and estimated the SPFs using both the negative binomial (NB) model and the heterogeneous negative binomial (HNB) model for analyzing the impacts of the model mis-specification on the mean and dispersion functions in SPF. In addition, this study analyzed the characteristics of errors in the crash reduction factors (CRFs) obtained when the two models are used to estimate the posterior means and variances, which are essentially estimated through the estimated hyper-parameters in the heterogeneous prior distributions. The simulation study results showed that a mis-estimation on the heterogeneous dispersion parameters through the NB model does not affect the coefficient of the mean functions, but the variances of the prior distribution are seriously mis-estimated when the NB model is used to develop SPFs without considering the heterogeneity in dispersion. Consequently, when the NB model is used erroneously to estimate the prior distributions with heterogeneous dispersion parameters, the mis-estimated posterior mean can produce large errors in CRFs up to 120%.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.4
• /
• pp.737-743
• /
• 2014

This experiment was conducted to compare heterogeneity for the variance in dairy cattle population and to induce homogeneity of variance using 502,228 performance test records of dairy cattle. The estimates of heritability for milk yields, fat yields and protein yields were 0.28, 0.26 and 0.24, respectively and the estimate of average breeding value by birth year was lower in HV (heterogenous variance) model than in animal model, collectively. The average breeding values of milk yields, fat yields and protein yields for 545 sire bulls applicable to the criteria of interbull MACE programme were 453.54kg, 10.75kg and 14.33kg, respectively and when the heterogeneity was adjusted they were 432.06kg, 10.15kg and 13.40kg, respectively, which were lower in all milk traits collectively. In animal model, coefficients of phenotypic correlation between dataset I and II were 0.839 in milk yields, 0.821 in fat yields, and 0.837 in protein yields, while in HV model, they were 0.841 in milk yields, 0.820 in fat yields, and 0.836 in protein yields, showing similar results in 2 models. When compared using animal model and HV model, the regression coefficient for ratio of number of daughters by calving year of milk yields increased from 15.157 to 16.105 and that of fat yields increased from =0.227 to =0.196, but that of protein yields decreased from 0.630 to 0.586.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.284-284
• /
• 2023

도시 침수의 발생과 규모는 도시 유역이 가지는 짧은 도달 시간으로 인하여 주로 시단위 이하의 짧은 지속시간의 강우의 극한 및 변동성에 따라 결정된다. 미래 기간에 대하여 도시 수문 시스템의 적정성을 평가하기 위해서는 기후변화에 따른 시단위 이하 강우의 특성을 살펴보아야한다. 그러나 기후변화 영향 평가 도구로 활용되는 기후 모형들은 대부분 일단위의 결과물을 제공하여 시단위 이하의 미세 규모 강우의 특성을 나타낼 수 없다. 이에 따라 본 연구에서는 기후 모형 모의 결과와 포아송 클러스터 강우 모형을 이용하여 미래 시단위 이하 강우 시계열을 모의하는 방법을 제안한다. 첫째로, 포아송 클러스터 기반 강우 생성 알고리즘과 폭풍우 재배열 알고리즘을 결합한 최신 모형을 선정하였다. 해당 모형은 광범위한 시간 규모에서 관측된 강우량의 주요 통계와 극값을 재현할 수 있는 모형이다. 그 다음 강우 모형에 적합시킬 관측 강우량 통계(평균, 분산, 공분산, 왜도, 우기 비율)를 계산하였다. 둘째, 강우 통계 간의 선형 관계를 도출하였다. 여기서는 클러스터에 있는 모든 관측소의 통계를 사용하여 회귀의 신뢰도를 높였다. 셋째, 강우 평균 조정을 위한 Change Factor는 제어(2000~2019년) 및 미래(2041~2070년) 기간의 기후 모형 자료를 사용하여 계산하였다. 넷째, 조정된 15분 강우 평균은 관측 평균에 Change Factor을 곱하여 계산하고 조정된 강우 평균과 통계 간의 관계를 사용하여 미래 강우 통계 세트를 추정하였다. 여러 통계 세트를 생성한 후 마지막으로 미래 통계에 강우 모형을 적합시켜 최종적으로 미래 시단위 이하 강우 시계열을 모의하였다. 이 방법은 CMIP6에 참여하는 기후 모델의 기후 예측 데이터를 사용하여 용산(415) 및 동래(940) AWS 관측소에 적용되었다. 두 관측소의 미래 강우 모의 결과, 시단위 이하 시간 규모에서 극값이 증가하는 추세를 보였다.

• Journal of the Korean Statistical Society
• /
• v.4 no.1
• /
• pp.9-17
• /
• 1975

A, B 두 요인의 영향을 받고 있다고 생각되는 rc개 측정치가 있고 이것이 다음과 같이 $r\timesc$ 이차분류표로 정리되었다고 하자. 여기에서 $$y_{ij} = \mu + \alpha_i + \beta_j + \epsilon_{ij}$$ 와 같은 가법모형을 생각한다. 그리고 $\epsilon_{ij}$는 잔여항으로써 평균이 0, 분산이 $\sigma^2$인 정규분포를 한다고 가정하는 것이 보통이다. 또 이것은 모수모형인 경우 $E(y_{ij}) = \mu + \alpha_i + \beta_i, v(y_{ij}) = \sigma^2$임을 의미하는 것으로 생각된다. 그러나 자료에 따라서는 위에서와 같은 가법적 모형을 적용한다는 것이 적당하지 못한 경우가 있다.

• Journal of Korea Water Resources Association
• /
• v.31 no.6
• /
• pp.795-806
• /
• 1998

Soil moisture is affected by regional climate, soil characteristics and land surface condition, etc,. Especially, the changes in land surface condition is more than other factors, which is mainly due to rapid urbanization and industrialization. This study is to evaluate how the change of land surface condition impacts on soil moisture field evolution using a simple model of soil moisture dynamics. For the quantification of soil moisture field, the first half of the paper is spared for the statistical characterization based on the first- and second-order statistics of Washita '92 and Monsoon '90 data. The second half is for evaluating the impact of land cover changes through simulation study using a model for soil moisture dynamics. The model parameters, the loss rate and the diffusion coefficient, have been estimated using the observed data statistics, where the changes of surface conditions are considered into the model by applying various parameter sets with different second-order statistics. This study is concentrated on evaluating the impact due to the changes of land surface condition variability. It is because we could easily quantify the impact of the changes of its areal mean based on the linear reservoir concept. As a result of the study, we found; (1)as the variability of land surface condition, increases, the soil moisture field dries up more easily, (2)as the variabilit y of the soil moisture field is the highest at the beginning of rainfall and decreases as time goes on to show the variability of land surface condition, (3)the diffusion effect due to surface runoff or water flow through the top soil layer is limited to a period of surface runoff and its overall impact is small compared to that of the loss rate field.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.5
• /
• pp.1025-1038
• /
• 2014

Linear mixed model has often been utilized for genetic association analysis with family-based samples. The correlation matrix for family-based samples is constructed with kinship coefficient and assumes that parental phenotypes are independent and the amount of correlations between parent and offspring is same as that of correlations between siblings. However, for instance, there are positive correlations between parental heights, which indicates that the assumption for correlation matrix is often violated. The statistical validity and power are affected by the appropriateness of assumed variance covariance matrix, and in this thesis, we provide the linear mixed model with flexible variance covariance matrix. Our results show that the proposed method is usually more efficient than existing approaches, and its application to genome-wide association study of body mass index illustrates the practical value in real data analysis.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.749-753
• /
• 2010

본 논문에서는 하천에 유입되는 오염물질 중 대부분을 차지하는 비보존성 오염물질의 확산거동을 분석하기 위해 2차원 수심 평균된 이송분산방정식에 유한요소법을 적용하였다. 수치모형 구성을 위해 SUPG(Streamline-upwind Petrov-Galerkin)법을 이용한 가중잔차법을 사용하였다. 모의대상 수질인자는 BOD와 DO이며, BOD 농도 결과가 DO 농도 계산에서의 입력 자료로 이용되도록 상호 연계를 형성하였다. 모형의 검증을 위하여 직사각형 수로에 선원으로 연속주입하여 얻은 수치해와 해석해를 비교하였다. 비교결과 수치해와 해석해의 결과가 서로 일치하는 것을 볼 수 있었다.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.6
• /
• pp.1449-1466
• /
• 2014

In this paper, we consider a hedge portfolio based on futures of underlying asset. A classical way to estimate a hedge ratio for a hedge portfolio of a spot and futures is a regression analysis. However, a regression analysis is not capable of reflecting long-run equilibrium between a spot and futures and volatility clustering in the conditional variance of financial time series. In order to overcome such defects, we analyzed KOSPI200 index and futures using VECM-CC-GARCH model and computed a hedge ratio from the estimated conditional covariance-variance matrix. In real data analysis, we compared a regression and VECM-CC-GARCH models in terms of hedge effectiveness based on variance, value at risk and expected shortfall of log-returns of hedge portfolio. The empirical results show that the multivariate GARCH models significantly outperform a regression analysis and improve hedging effectiveness in the period of high volatility.

• The Korean Journal of Applied Statistics
• /
• v.29 no.3
• /
• pp.449-462
• /
• 2016

This paper considers a long-run variance estimation using a block bootstrap method under strong dependence also known as long range dependence. We extend currently available methods in two ways. First, it extends bootstrap methods under short range dependence to long range dependence. Second, to accommodate the observation that strong dependence may come from deterministic trend plus noise models, we propose to utilize residuals obtained from the nonparametric kernel estimation with the bimodal kernel. The simulation study shows that our method works well; in addition, a data illustration is presented for practitioners.