Energy Risk Measure Prediction in ARMA(1,1)-GARCH(1,1) Volatility Models
The existence of extreme volatility due to increased price changes causes gre- ater risks and uncertainties to be faced. To minimize risk, it is necessary to predict volatility and risk measures. The model that can be used to predict vo- latility is a combination of ARMA(1,1) and GARCH(1,1) model...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/39118 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | The existence of extreme volatility due to increased price changes causes gre-
ater risks and uncertainties to be faced. To minimize risk, it is necessary to
predict volatility and risk measures. The model that can be used to predict vo-
latility is a combination of ARMA(1,1) and GARCH(1,1) models. ARMA(1,1)-
GARCH(1,1) model is effective to be used in the mean of energy stock prices
and asymmetric volatility that coincide with the leverage effect. While in the
calculation of risk measures, the method used is Value-at-Risk (VAR).
The results obtained in this thesis are that the ARMA(1,1)-GARCH(1,1) mo-
del is good enough to be used in modeling volatility, where the ARMA(1,1)
-GARCH(1,1) model can capture the empirical characteristics of volatility.
Predictions with historical volatility are more accurate than realized volatility.
Furthermore, in predicting the energy risk measure, the distribution that is
suitable for use is students't distribution. |
|---|