• The Korean Journal of Applied Statistics
• /
• v.20 no.2
• /
• pp.291-311
• /
• 2007

With a series of unexpected huge losses in the financial markets around the world recently, especially in the insurance market with extreme loss cases such as catastrophes, there is an increasing demand for risk management for extreme loss exposures due to high unpredictability of those risks. For extreme risk management, to make a maximum use of the information concerning the tail part of a loss distribution, EVT(Extreme Value Theory) modelling nay be the best to analyze extreme values. The Extreme Value Theory is widely used in practice and, especially in financal markets, EVT modelling is getting popular to analyBe the effects of extreme risks. This study is to review the significance of the Extreme Value Theory in risk management and, focusing on analyzing insurer's risk capital, extreme risk is measured using the real fire loss data and insurer's specific amount of risk capital is figured out to buffer the extreme risk.

• Communications for Statistical Applications and Methods
• /
• v.13 no.2
• /
• pp.389-407
• /
• 2006

Extreme value theory has been used widely in many areas of science and engineering to deal with the assessment of extreme events which are rare but have catastrophic consequences. The potential of extreme value theory has only been recognized recently in finance area. In this paper, we provide an overview of extreme value theory for estimating and assessing value at risk and expected shortfall which are the methods for modelling and measuring the extreme financial risks. We illustrate that the approach based on extreme value theory is very useful for estimating tail related risk measures through backtesting of an empirical data.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.3
• /
• pp.593-603
• /
• 2004

We consider the problem of estimating the scale parameter of the Weibull distribution based on multiply Type-II censored samples. We propose two estimators by using the approximate maximum likelihood estimation method for Weibull and extreme value distributions. The proposed estimators are compared in the sense of the mean squared error.

• Communications for Statistical Applications and Methods
• /
• v.3 no.2
• /
• pp.249-273
• /
• 1996

This paper reviews and develops several statistical models for extreme values, based on threshold methodology. Extreme values of a time series are modeled in terms of tails which are defined as truncated forms of original variables, and Markov property is imposed on the tails. Tails of the generalized extreme value distribution and a multivariate extreme value distributively, of the tails of the series. These models are then applied to real ozone data series collected in the Chicago area. A major concern is given to detecting any possible trend in the extreme values.

• Journal of the Korean Society of Safety
• /
• v.25 no.3
• /
• pp.112-117
• /
• 2010

This study presents a methodology to evaluate the driving safety of vehicles against localized high wind on the roads over the valleys or along the coasts. Risk level for vehicle accident is derived from the side slip caused by cross wind, and then safety criteria based on reliability for driving stability are defined. The level of safety is classified according to probability of exceeding against wind speed using the concept of extreme value statistics. To attain the safety level of vehicle on bridges, numerical simulations using Computational Fluid Dynamics(CFD) are performed. Based on this result, risk reduction and quality improvement is expected through analysis for each alternative in bridges design, construction and operation & maintenance stage with proposed process

• The Korean Journal of Applied Statistics
• /
• v.33 no.1
• /
• pp.107-114
• /
• 2020

Extreme value distributions have often been used for the analysis (e.g., prediction of return level) of data which are observed from natural disaster. By the extreme value theory, the block maxima asymptotically follow the generalized extreme value distribution as sample size increases; however, this may not hold in a small sample case. For solving this problem, this paper proposes the use of a log-logistic (LLG) distribution whose validity is evaluated through goodness-of-fit test and model selection. The proposed method is illustrated with data from annual maximum earthquake magnitudes of China. Here, we present the predicted return level and confidence interval according to each return period using LLG distribution.

• Communications for Statistical Applications and Methods
• /
• v.29 no.3
• /
• pp.319-331
• /
• 2022

In this paper, we develop a new statistical model to forecast the PM_2.5 level in Seoul, South Korea. The proposed model is based on the extreme quantile regression model with lasso penalty. Various meteorological variables and air pollution variables are considered as predictors in the regression model, and the lasso quantile regression performs variable selection and solves the multicollinearity problem. The final prediction model is obtained by combining various extreme lasso quantile regression estimators and we construct a binary classifier based on the model. Prediction performance is evaluated through the statistical measures of the performance of a binary classification test. We observe that the proposed method works better compared to the other classification methods, and predicts 'very bad' cases of the PM_2.5 level well.

• Journal of the Korean Statistical Society
• /
• v.30 no.3
• /
• pp.419-433
• /
• 2001

In this paper we introduce a method of improving efficiency of the moment estimator of Dekkers, Einmahl and de Haan(1989) for the extreme value index $\beta$. a new estimator of $\beta$ is proposed by adding the third moment ot the original moment estimator which is composed of the first two moments of the log-transformed sample data. We establish asymptotic normality of the new estimator and examine and adaptive procedure for the new estimator. The resulting adaptive estimator proves to be asymptotically better than the moment estimator particularly for $\beta$<0.

• Communications for Statistical Applications and Methods
• /
• v.15 no.5
• /
• pp.793-798
• /
• 2008

Extreme value inference deals with fitting the generalized extreme value distribution model and the generalized Pareto distribution model, which are recently combined to give a single model, namely a two-dimensional non-homogeneous Poisson exceedance point process model. In this paper, we extend the two-dimensional non-homogeneous Poisson process model to include non-stationary effect or dependence on covariates and then derive the likelihood for the extended model.

• Journal of the Korean Data and Information Science Society
• /
• v.16 no.3
• /
• pp.629-638
• /
• 2005

We derive the approximate maximum likelihood estimators of the scale parameter and location parameter of the extreme value distribution based on multiply Type-II censored samples. We compare the proposed estimators in the sense of the mean squared error for various censored samples.