APLIKASI EGARCH UNTUK PERAMALAN VAR; AN EGARCH APPLICATION FOR VAR FORECASTING

SOMASIH DWIPA, NENDRA MURSETYA, Dedi Rosadi

2016 | Disertasi | FMIPA

A time series data of stock returns are one of type time series data that has a high volatility and different variance in every point of time. Such data are volatile, set up a pattern of asymmetrical, having a nonstationary model, and that does not have a constant residual variance (heteroscedasticity). A time series ARCH and GARCH model can explain the heterocedasticity of data, but the ARCH-GARCH models are not always able to fully capture the asymmetric property of high frequency. The Exponential Generalized Autoregresive Heteroskedascticity (EGARCH) model can cover up GARCH weaknesses in capturing asymmetry good news and bad news taking into the leverage effect. Furthermore EGARCH models were used to estimate the value of VaR as the maximum loss that will be obtained during a certain period at a certain confidence level. The aim of this study was to determine the best forecasting model of Jakarta Composite Index (JSI). The model had used in this study are ARCH, GARCH, and EGARCH. Results from this study indicate that the EGARCH (1,1) is the best model with maximum value of log-likelihood and the the minimum value of statistical information criteria. Model EGARCH (1,1) has a value of log likelihood 1558.212 with the value of information criteria AIC = -2.5430; BIC = -2.5137; SIC = -2.5430; and HQIC = -2.5319. This model get a value of Value at Risk (VaR) of the period with 95% of confidence level is Rp 3.663.128,13 for Rp500,000,000.00 investment funds.

Kata Kunci : Forecasting, volatility, EGARCH, VaR