• The Korean Journal of Applied Statistics
• /
• v.24 no.2
• /
• pp.293-305
• /
• 2011

The volatility is one of most important parameters in the areas of pricing of financial derivatives an measuring risks arising from a sudden change of economic circumstance. We propose a Bayesian approach to estimate the volatility varying with time under a linear model with ARMA(p, q)-GARCH(r, s) errors. This Bayesian estimate of the volatility is compared with the ML estimate. We also present the probability of existence of the unit root in the GARCH model.

• Journal of Digital Convergence
• /
• v.10 no.9
• /
• pp.357-362
• /
• 2012

We have compared and predicted for non-linear time series data which are real data having different variences using GRCA(1) model and neural network method. In particular, using Korea Composite Stock Price Index rate, mean square errors of prediction are obtained in genaralized random coefficient autoregressive model and neural network method. Neural network method prove to be better in short-term forecasting, however GRCA(1) model perform well in long-term forecasting.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.5
• /
• pp.839-847
• /
• 2011

In this study, we derive an estimator based on autocovariance for the regression coefficients vector in the multiple linear regression model. This method is suggested by Park (2009), and although this method does not seem to be intuitively attractive, this estimator is unbiased for the regression coefficients vector. When the vectors of exploratory variables satisfy some regularity conditions, under mild conditions which are satisfied when errors are from autoregressive and moving average models, this estimator has asymptotically the same distribution as the least squares estimator and also converges in probability to the regression coefficients vector. Finally we provide a simulation study that the forementioned theoretical results hold for small sample cases.

• The Journal of the Korea Contents Association
• /
• v.17 no.12
• /
• pp.77-91
• /
• 2017

Due to the lack of learning motivation, there is a need to seek ways to facilitate learning incentives because it's causing drop out and maladjustment of university life. This study is to examine whether the ARCS evaluation model developed by Keller (1983) is a valid model for evaluating the motivation level of local university students sample 276(male 116, female 157) in the Republic of Korea. To analyze the data, average statistic, one-way ANOVA and confirmative factor analysis were used. The conclusion of this study is as follows. First, the level of motivation per ARCS factor has demonstrated the highest relevance factor. Second, the level of motivation by the ARCS for the 1st and 3rd graders was appropriate. Differences in 'attention' and 'relevance' have only been observed for each year, and the 1st grade group was found to be larger than the 2nd grade cohort. Third, construct validity and convergent validity were obtained for measuring the level of motivation. The results of the verification of the variables also showed that the AVE and CR were met, and the model fit well was satisfactory. Based on the finding results, discussion and implication for further research were suggested.

• The Korean Journal of Applied Statistics
• /
• v.3 no.2
• /
• pp.79-89
• /
• 1990

For selecting a subset of k normal populations containing the one with the largest mean, a Bayes-$P^*$ selection procedure is considered when the common variance is unknown. Performance of the Bayes-$P^*$ selection procedure is compared with a well known classical procedure through a simulation study. Some frequentist's characteristics of Bayes-$P^*$ procedure are also studied.

• Journal of Korea Water Resources Association
• /
• v.42 no.11
• /
• pp.897-909
• /
• 2009

The relative contribution of between hillslope-flow and stream-flow by heterogeneity of drainage path are quantitatively assessed in the present study with GIUH model based on grid of GIS. Application watersheds are selected Pyeongchang, Bocheong and Wi river basin of IHP in Korea. The mean and variance of hillslope and stream length are estimated and analyzed in each watershed. And coupling with observation storm events, estimate hillslope and stream characteristic velocity which dynamic parameters of GIUH model. The mean and variance of distribution of travel time (i.e. IUH) calculate using estimated pass lengths and characteristic velocities. And the relative contributions are assessed by heterogeneity of drainage path. As a result, the effect of the variance that determine shape of IUH dominate with hillslope's effect in the small watershed area (within 500 $km^2$). Thus, GIUH in the small watershed area must consider hillslope-flow.

• Journal of Korea Water Resources Association
• /
• v.43 no.4
• /
• pp.399-408
• /
• 2010

The sensitivity of Nash model parameters is analyzed about characteristic velocities considering geomorphological dispersion in the present study. And changing shape of IUH compared and analyzed as variation of characteristic velocities through numerical experiment. Application watersheds are selected 4 subwatersheds which are located at main stream of Bocheong basin. The mean and variance of hillslope and stream path length are estimated in each watershed with GIS. And Nash model parameters are estimated with moments of path lengths and characteristic velocities. The changing trend about IUH which is derived Nash model parameters are compared as variation of characteristic velocities. The Major results of this study are summarized as follows. The Nash model parameters sensitively present changes about hillslope characteristic velocity. And the effect of the peak discharge and shape of recession in IUH dominate with hillslope's characteristic velocity, the effect of the peak time and shape of ascension in IUH dominate with channel's characteristic velocity.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.200-200
• /
• 2021

하천은 용수공급, 관개, 친수활동, 산업활동 등 인간의 활동에 중요한 역할을 한다. 이에 따라 수질관리는 필수적이며 유기물, 중금속, 화학물질 등의 용존물질들은 수질문제에 직접적으로 영향을 미친다. 따라서 하천에서의 용존물질의 혼합 거동을 파악하기 위한 연구가 지난 수십년간 이루어지고 있다. 하천 흐름에 따른 오염물질의 이동 및 확산 거동을 예측하기 위하여 1차원 추적모형이 활용되는데, 그 중 하천저장대 모형(Transient Storage Model, TSM)은 자연하천의 복잡하고 불규칙한 수리·지형적인 특성을 단순하게 반영할 수 있다는 장점때문에 가장 많이 사용된다. 하지만 TSM은 매개변수에 대한 의존성과 불확도가 크며, TSM의 저장대에서의 농도분포에 대한 지수함수형태의 모델링이 하상간극수역(Hyporheic zone)에서의 저장대 특성을 반영하기에 구조적으로 부정확하다는 단점이 제기되고 있다. 최근 이러한 TSM의 단점을 보완하고 하천에서의 저장대 메커니즘을 보다 정확하게 구현하고자 체류시간분포(residence time distribution)를 이용한 확률론적 저장대 모델링 프레임워크가 등장하고 있다. 본 연구에서는 본류대와 저장대에서의 오염물질의 체류시간분포를 분리하여 해석하고 이를 전달함수(transfer function)를 이용한 합성곱으로 결합한 형태의 프레임워크를 적용하여 모델링하였다. 상기의 모형을 검증하기 위하여 2019년 감천의 4.85km 구간에서 추적자 실험을 실시하였다. 실험 당시 유량은 12.9 m³/s로 풍수기에 해당되며 평균 유속은 약 0.6 m/s로 측정되었다. 모형의 매개변수는 추적자 실험으로부터 최적화 기법을 통해 역모델링기법으로 결정하였다. 제안된 모형에 의한 모의 결과를 추적자 실험에서의 농도측정자료와 비교한 결과, 평균 0.988의 결정계수를 보여 매우 높은 정확도를 보이고 있음을 알 수 있었다. 저장대특성을 나타내는 농도곡선의 꼬리부에 대하여 같은 조건에서 1차원 이송-분산(ADE) 모형, TSM의 모의결과와도 비교한 결과 본 모형은 추적자 실험 농도측정 결과와 평균 0.195의 오차율을 보이며, 이는 ADE 모형과 TSM의 오차율인 14.03과 1.866에 비해 매우 정확한 것으로 나타났다.

• Journal of Korea Water Resources Association
• /
• v.54 no.11
• /
• pp.863-873
• /
• 2021

The mechanical dispersion which dominates solute transport in porous media is caused by the difference in flow velocity within pores. Longitudinal dispersion coefficient and longitudinal dispersivity that are hydro-dispersive parameters of advection-dispersion equation can only be obtained by experiment. Hydraulic mean radius that represents the amount and intensity of flowing water within pores can be obtained by the formula using the factors for physical properties. A slug injection test was conducted and a power type empirical formula for obtaining a longitudinal dispersivity using a hydraulic mean radius in rockfill porous media was derived. It is possible to obtain the longitudinal dispersivity depending on transport distance because it contains a formula for a scale constant, and expected to be applicable to waterways filled with homogeneous gravel and small flow rate.

• The Korean Journal of Applied Statistics
• /
• v.6 no.2
• /
• pp.253-263
• /
• 1993

Recent interest in Taguchi's methods have led to developments of joint modelling of the mean and dispersion in generalized linear models. Since a single data transformation cannot produce all the necessary conditions for an analysis, for the analysis of the Taguchi data, the use of the generalized linear models is preferred to a commonly used data transformation method. In this paper, we will illustrate this point and provide GLIM macros to implement the joint modelling of the mean and dispersion in generalized linear models.