• Journal of the Korean Data and Information Science Society
• /
• v.28 no.4
• /
• pp.797-810
• /
• 2017

The Korean peninsula is exposed to typhoons every year. Typhoons cause huge socioeconomic damage because tropical cyclones tend to occur with strong winds and heavy precipitation. In order to understand the complex dependence structure between strong winds and heavy precipitation, the copula links a set of univariate distributions to a multivariate distribution and has been actively studied in the field of hydrology. In this study, we carried out analysis using data of wind speed and precipitation collected from the weather stations in Busan and Jeju. Log-Normal, Gamma, and Weibull distributions were considered to explain marginal distributions of the copula. Kolmogorov-Smirnov, Cramer-von-Mises, and Anderson-Darling test statistics were employed for testing the goodness-of-fit of marginal distribution. Observed pseudo data were calculated through inverse transformation method for establishing the copula. Elliptical, archimedean, and extreme copula were considered to explain the dependence structure between strong winds and heavy precipitation. In selecting the best copula, we employed the Cramer-von-Mises test and cross-validation. In Busan, precipitation according to average wind speed followed t copula and precipitation just as maximum wind speed adopted Clayton copula. In Jeju, precipitation according to maximum wind speed complied Normal copula and average wind speed as stated in precipitation followed Frank copula and maximum wind speed according to precipitation observed Husler-Reiss copula.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.267-277
• /
• 2016

This paper considers we consider the estimation of copula parameters based on residuals in stochastic regression models. We prove that a semiparametric estimator using residual empirical distributions is consistent under some conditions and apply the results to the copula-ARMA model. We provide simulation results for illustration.

• The Korean Journal of Applied Statistics
• /
• v.30 no.2
• /
• pp.203-213
• /
• 2017

We study estimation and inference of joint conditional distributions of bivariate longitudinal outcomes using regression models and copulas. We consider a class of time-varying transformation models and combine the two marginal models using Gaussian copulas to estimate the joint models. Our models and estimation method can be applied in many situations where the conditional mean-based models are inadequate. Gaussian copulas combined with time-varying transformation models may allow convenient and easy-to-interpret modeling for the joint conditional distributions for bivariate longitudinal data. We apply our method to an epidemiological study of repeatedly measured bivariate cholesterol data.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.3
• /
• pp.689-700
• /
• 2016

We study estimation and inference of the joint conditional distributions of bivariate longitudinal outcomes using regression models and copulas. For the estimation of marginal models we consider a class of time-varying transformation models and combine the two marginal models using nonparametric empirical copulas. Regression parameters in the transformation model can be obtained as the solution of estimating equations and our models and estimation method can be applied in many situations where the conditional mean-based models are not good enough. Nonparametric copulas combined with time-varying transformation models may allow quite flexible modeling for the joint conditional distributions for bivariate longitudinal data. We apply our method to an epidemiological study of repeatedly measured bivariate cholesterol data.

• Journal of Korea Water Resources Association
• /
• v.52 no.12
• /
• pp.985-999
• /
• 2019

Over the last decade, droughts have become more severe and frequent in many regions, and several studies have been conducted to explore the recent drought. Copula-based bivariate drought frequency analysis has been widely used to evaluate drought risk in the context of point frequency analysis. However, the relatively significant uncertainties in the parameters are problematic when available data are limited. For this reason, the primary purpose of this study is to develop a regional drought frequency model based on the Copula function. All parameters, including marginal and copula functions in the regional frequency model, were estimated simultaneously. Here, we present a case study of recent drought 2013-2015 over the Han-River watershed where severe drought risk is consistently found to increase. The proposed model provided a reliable way to significantly reduce the uncertainty of parameters with a Bayesian modeling framework. The uncertainty of the joint return period in the regional frequency analysis is nearly three times lower than that of the point frequency analysis. Accordingly, DIC values in the regional frequency analysis model are significantly decreased by 15. The results confirm that the proposed model is not only reliably representing characteristics of historical droughts and dependencies between drought variables, but also providing the efficacy of understanding regional drought characteristics.

• Management & Information Systems Review
• /
• v.30 no.4
• /
• pp.359-383
• /
• 2011

One of the representative prudential regulations is the capital regulation. The current regulation and international criteria are just simply adding up the market risk and credit risk. According to the portfolio theory due to diversification effect the total risk is less than the summation of market and credit risk. This paper investigates to verify the existence of diversification effect in measuring the integrated risk of financial firm by the copula function, which is combine the different distribution maintain their propriety. The result of the test shows that in measuring the integrated risk not only the correlation and but also the proprieties of market and credit risk distribution are very important. And the tail of risk distribution is important when measuring the economic capital, especially the external impact to the financial market. This paper's contribution is that the empirical evidence in considering the relationship between market and credit risk the integrated risk is less than sum of them.

• Journal of Korea Water Resources Association
• /
• v.48 no.12
• /
• pp.969-979
• /
• 2015

This study applied a probabilistic-based hidden Markov model (HMM) to better characterize drought patterns. In addition, a copula-based bivariate drought frequency analysis was employed to further investigate return periods of the current drought condition in year 2015. The obtained results revealed that western Kangwon area was generally more vulnerable to drought risk than eastern Kangwon area using the 40-year data. Imjin-river watershed including Cheorwon area was the most vulnerable area in terms of severe drought events. Four stations in Han-river watershed showed a joint return period exceeding 1,000 years associated with the drought duration and severity in 2014-2015. Especially, current drought status in Northern Han-river and Imjin-river watershed is most severe drought exceeding 100-year return period.

• Journal of Digital Convergence
• /
• v.11 no.9
• /
• pp.103-111
• /
• 2013

As the demand-oriented management has been getting important in Supply Chain Management (SCM), various forecasting methods have been suggested including regression analyses. However, dependency structures among variables have been captured by a correlation coefficient, only. It results in inaccurate demand predictions. This paper suggests a new and effective forecasting modeling framework using student's t-copula function. In order to show overall modeling procedures framework, heavy tail typed numerical data and its copula estimations are provided. The suggested methodology can contribute to decrease the bullwhip effect and to stabilize volatile environment in a supply chain network.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.299-299
• /
• 2022

수문학적 가뭄 발생의 직접적 영향은 강수부족량이나, 다양한 사회경제적 인자들은 수문학적 가뭄에 간접적으로 영향을 미치고 있다. 물관리 선진기관에서는 인간의 활동 및 물관리 방식에 따라 수문학적 가뭄을 심화시키거나 완화시킬 수 있음을 인지하고, 인간의 물사용이 가뭄에 미치는 영향을 평가하기 위한 다양한 연구가 이루어지고 있다. 본 연구에서는 강수량 및 미래의 인구변화에 따른 수문학적 가뭄의 영향의 정도를 판단함으로써, 인간의 활동이 가뭄에 미치는 영향을 정량적으로 제시하고자 한다. 충정북도 시군지역을 대상지역으로 선정하였으며, 시군 장래인구 추정값을 미래 인구자료로, 미래 유출량이 산정되어 제공되는 RCP 4.5와 RCP 8.5시나리오를 활용하여 미래 가뭄상황 예측하였다. 강수량 및 인구변화가 수문학적 가뭄에 미치는 영향 평가를 위하여 코플라함수 기반의 베이지안 네트워크 모형이 활용하였다. 베이지안 네트워크는 강수량, 인구밀도, 수문학적 가뭄사이의 관계 도출을 위하여 활용되었으며, 베이지안 네트워크 내의 결합확률의 산정을 위하여 코플라 함수가 활용되었다. 미래의 강수량 및 인구밀도의 변화에 따른 수문학적 가뭄의 영향 관계를 분석한 결과는 다음과 같다. 강수량이 인구밀도보다 수문학적 가뭄의 발생에 영향을 미치며, 약 0.2~0.3 정도 발생확률이 크게 산정되었다. 두 인자를 동시에 고려할 경우, 강수량이 적고, 인구밀도가 높아지는 조건(F(강수량)=0.1, F(인구밀도)=0.9)에서는 조건부 CDF 변화율이 크게 나타나, 곧 수문학적 가뭄의 위험성이 높음을 확인할 수 있었다. 인구밀도는 수문학적 가뭄의 발생 위험성을 높이 알려져 있으나, 정량적으로 그 값을 제시한 연구 사례는 찾기 어렵다. 이에 따라 본 연구에서는 가뭄의 영향정도를 정량적으로 표현하였으며, 한 인자만의 영향이 아닌 두 개 이상의 인자들의 복합적인 영향 정도를 제시함으로써 수치적인 비교가 가능하게 하였다. 미래 추정 인자가 인구자료가 한정적이라 인구 자료만을 활용하여 수문학적 가뭄에 미치는 영향을 분석하였으나, 다른 사회경제적 지표를 활용하여 미래 변화에 따른 미래 수문학적 가뭄의 영향 정도의 비교 및 분석 결과를 바탕으로 가뭄 대응 우선순위 선정을 위한 연구자료로 활용 가능할 것으로 사료된다.

• Journal of Korea Water Resources Association
• /
• v.54 no.7
• /
• pp.523-534
• /
• 2021

Meteorological drought originates from a precipitation deficiency and propagates to agricultural and hydrological droughts through the hydrological cycle. Comparing with the meteorological drought, agricultural and hydrological droughts have more direct impacts on human society. Thus, understanding how meteorological drought evolves to agricultural and hydrological droughts is necessary for efficient drought preparedness and response. In this study, meteorological and hydrological droughts were defined based on the observed precipitation and the synthesized streamflow by the land surface model. The Bayesian network model was applied for probabilistic analysis of the propagation relationship between meteorological and hydrological droughts. The copula function was used to estimate the joint probability in the Bayesian network. The results indicated that the propagation probabilities from the moderate and extreme meteorological droughts were ranged from 0.41 to 0.63 and from 0.83 to 0.98, respectively. In addition, the propagation probabilities were highest in autumn (0.71 ~ 0.89) and lowest in winter (0.41 ~ 0.62). The propagation probability increases as the meteorological drought evolved from summer to autumn, and the severe hydrological drought could be prevented by appropriate mitigation during that time.