The Performance of Hybrid ARIMA-GARCH Modeling in Forecasting Gold Price

• Main Authors: Siti Roslindar, Yaziz, Noor Azlinna, Azizan, Roslinazairimah, Zakaria, Maizah Hura, Ahmad
• Format: Conference or Workshop Item
• Language: English
• Published: 2013
• Subjects: QA76 Computer software
• Online Access: http://umpir.ump.edu.my/id/eprint/4260/1/fist-2013-roslindar-the_performance_of.pdf; http://umpir.ump.edu.my/id/eprint/4260/; http://www.mssanz.org.au/modsim2013/F2/yaziz.pdf

In any type of investment, risk and return of the asset is very important to investors. Since 2000s, gold has been considered as a valuable precious metal. It is the most popular commodity and is categorized as a healthy return investment. Hence, the models that reflect the structure and pattern of the gold price and its forecasting accuracy become very significant to investors. This study assesses the performance of hybridization of potential univariate time series specifically ARIMA models with the superior volatility model, GARCH incorporates with the formula of Box-Cox transformation in analyzing and forecasting gold price. The Box-Cox transformation is used as the data transformation due to its potential best practice in normalizing data, stabilizing variance and reducing heteroscedasticity. The performance of the proposed model is analyzed by employing the hybrid model using daily gold price data series. Empirical results indicate that the proposed hybrid model ARIMA-GARCH has effectively improved the estimating and forecasting accuracy and provide the optimum results compared to the previous studies. The findings suggest that the potential combination of powerful and flexibility of ARIMA and the strength of GARCH models in handling volatility and risk in the data series as well as to overcome the linear limitation in the ARIMA models made the hybridization of ARIMA-GARCH model as a new promising approach in modeling and forecasting gold price.