• Communications for Statistical Applications and Methods
• /
• v.15 no.6
• /
• pp.825-835
• /
• 2008

Multivariate GARCH(MGARCH) has been useful in financial studies and econometrics for modeling volatilities and correlations between components of multivariate time series. An obvious drawback lies in that the number of parameters increases rapidly with the number of variables involved. This thesis tries to resolve the problem by using dimension reduction technique. We briefly review both factor models for dimension reduction and the MGARCH models including EWMA (Exponentially weighted moving-average model), DVEC(Diagonal VEC model), BEKK and CCC(Constant conditional correlation model). We create meaningful portfolios obtained after reducing dimension through statistical factor models and fundamental factor models and in turn these portfolios are applied to MGARCH. In addition, we compare portfolios by assessing MSE, MAD(Mean absolute deviation) and VaR(Value at Risk). Various financial time series are analyzed for illustration.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.6
• /
• pp.1333-1343
• /
• 2014

Hansen and Lund (2005) documented that a univariate GARCH(1,1) model is no worse than other sophisticated GARCH models in terms of prediction errors such as MSPE and MAE. Here, we extend Hansen and Lund (2005) by considering multivariate GARCH models and incorporating risk management measures such as VaR and fail percentage. Our Monte Carlo simulations study shows that multivariate GARCH(1,1) model also performs well compared to asymmetric GARCH models. However, we suggest that actual model selection should be done with care in light of risk management. It is applied to the realized volatilities of KOSPI, NASDAQ and HANG SENG index for recent 10 years.

• Korean System Dynamics Review
• /
• v.2 no.2
• /
• pp.85-96
• /
• 2001

In the recent Internet environment, there are different competition patterns among competitors as it was before. As we see real world example such as Covisint in automobile industry and Exostar in aerospace industry, collaboration among competitors now takes place and industry-wide B2B marketplaces come into existence. Hence, we suggest the extended system dynamics simulation model based on Kim(2002)’s collaboration profit models in order to explain competitors’ collaboration in the e-business environment. After all, we investigate the necessity of collaboration between competitors, and show the presence of the optimal investment decision making to collaborate. We also show that the effect of collaboration is changed as varying the industry characteristics such as standardization and volatility.

• Journal of the Korean Data and Information Science Society
• /
• v.16 no.2
• /
• pp.271-281
• /
• 2005

Zokian(1993) and Li and Li(1996) developed TARCH(Threshold ARCH) model, considering the asymmetries in volatility. The models are based on Engle(1982)'s ARCH model and Bollerslev(1986)'s GARCH model. However, two TARCH models can be expressed a common model through Box Cox Power transformation, which was used by Higgins and Bera(1992) for developing NARCH(nonlinear ARCH) model. This article shows the PTARCH(Power transformation TARCH) model is necessary in some condition, and it checks the fact that PTARCH model has better performance comparing estimates and RMSE(Root Mean Square Error) with those of Zakoian's TARCH model and Li and Li's TARCH model. PTARCH model would give contribution in asymmetric study as well as heteroscedastic study.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1231-1242
• /
• 2019

This paper presents a two-dimensional attention-based long short-memory (2D-ALSTM) model for stock index prediction, incorporating input attention and temporal attention mechanisms for weighting of important stocks and important time steps, respectively. The proposed model is designed to overcome the long-term dependency, stock selection, and stock volatility delay problems that negatively affect existing models. The 2D-ALSTM model is validated in a comparative experiment involving the two attention-based models multi-input LSTM (MI-LSTM) and dual-stage attention-based recurrent neural network (DARNN), with real stock data being used for training and evaluation. The model achieves superior performance compared to MI-LSTM and DARNN for stock index prediction on a KOSPI100 dataset.

• The Korean Journal of Financial Management
• /
• v.20 no.1
• /
• pp.163-190
• /
• 2003

This study tests the hypothesis of market efficiency through the information spillover effects over price and volatility across countries by using open-to-close(daytime) returns and close-to-open(overnight) returns of NASDAQ, KOSDAQ and JASDAQ data from January 3, 1997 to December 21, 2000. Based on Granger-causality and time-varying AR(1)-GARCH(1, 1)-M models we document that the evidence of statistically significant conditional mean and volatility spillovers effects from the daytime returns and volatility of NASDAQ to the overnight returns and volatility of KOSDAQ is observed both before and after the IMF foreign currency crisis but not to the close-to-open return before the IMF foreign currency crisis. We can understand the information spillover effect from NASDAQ to KOSDAQ on the overnight rather than the daytime grows more significantly after the IMF foreign currency crisis. We also find the interactive information spillover effect between NASDAQ and JASDAQ both before and after the IMF financial crisis, in particular, to close-to-open return. In addition, the market efficiency between KOSDAQ and NASDAQ is on an increasing trend through IMF foreign currency crisis.

• The Korean Journal of Applied Statistics
• /
• v.27 no.6
• /
• pp.959-973
• /
• 2014

Asset pricing models that account for asymmetric volatility in asset prices have been recently proposed. This article presents an efficient Bayesian method to analyze asset-pricing models. The method is developed by devising a partially collapsed Gibbs sampler that capitalizes on the functional incompatibility of conditional distributions without complicating the updates of model components. The proposed method is illustrated using simulated data and applied to daily S&P 500 data observed from September 1980 to August 2014.

• The Korean Journal of Financial Management
• /
• v.24 no.3
• /
• pp.153-186
• /
• 2007

It is well known that the distributional properties of financial asset returns exhibit fatter-tails and skewer-mean than the assumption of normal distribution. The correct assumption of return distribution might improve the estimated performance of the Value-at-Risk(VaR) models in financial markets. In this paper, we estimate and compare the VaR performance using the RiskMetrics, GARCH and FIGARCH models based on the normal and skewed-Student-t distributions in two daily returns of the Korean Composite Stock Index(KOSPI) and Korean Won-US Dollar(KRW-USD) exchange rate. We also perform the expected shortfall to assess the size of expected loss in terms of the estimation of the empirical failure rate. From the results of empirical VaR analysis, it is found that the presence of long memory in the volatility of sample returns is not an important in estimating an accurate VaR performance. However, it is more important to consider a model with skewed-Student-t distribution innovation in determining better VaR. In short, the appropriate assumption of return distribution provides more accurate VaR models for the portfolio managers and investors.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.1053-1061
• /
• 2013

In this paper, we propose the time series forecasting models for internet traffic with long memory and heteroscedasticity. To control and forecast traffic volume, we first introduce the traffic forecasting models which are determined by the volatility and heteroscedasticity of the traffic. We then analyze and predict the heteroscedasticity and the long memory properties for forecasting traffic volume. Depending on the characteristics of the traffic, Fractional ARIMA model, Fractional ARIMA-GARCH model are applied and compared with the MAPE(Mean Absolute Percentage Error) Criterion.

• Journal of Korean Society of Transportation
• /
• v.33 no.1
• /
• pp.61-69
• /
• 2015

This study compares the forecasting accuracy of five econometric models on domestic total freight volume in South Korea. Applied five models are as follows: Ordinary Least Square model, Partial Adjustment model, Reduced Autoregressive Distributed Lag model, Vector Autoregressive model, Time Varying Parameter model. Estimating models and forecasting are carried out based on annual data of domestic freight volume and an index of industrial production during 1970~2011. 1-year, 3-year, and 5-year ahead forecasting performance of five models was compared using the recursive forecasting method. Additionally, two forecasting periods were set to compare forecasting accuracy according to the size of future volatility. As a result, the Time Varying Parameter model showed the best accuracy for forecasting periods having fluctuations, whereas the Vector Autoregressive model showed better performance for forecasting periods with gradual changes.