Amiri, Esmail (2015) Forecasting linear time series models with heteroskedastic errors in a Bayesian approach. In: 5th International Conference on Computing and Informatics (ICOCI) 2015, 11-13 August 2015, Istanbul, Turkey.

Preview

PDF Download (1MB) | Preview

Abstract

A study was conducted to compare the forecasting performance of four models, namely Stochastic Volatility (SV), Generalized Autoregressive Conditional Heteroskedasticity (GARCH), Autoregressive with GARCH errors (AR-GARCH) and Autoregressive with SV errors (AR-SV).Bayesian approach and Markov Chain Monte Carlo (MCMC) simulation methods are applied to estimate the parameters of the models and their predictive densities; using three time series data (daily Euro/US Dollar, British Pound/US Dollar and Iranian Rial/US Dollar exchange rates).Out-ofsample analysis through cumulative predictive Bayes factors clearly showed that modeling regression residuals heteroskedastic, substantially improves predictive performance, especially in turbulent times.A direct comparison of SV and vanilla GARCH(1,1) indicated that the former performs better in terms of predictive accuracy

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	ISBN No: 978-967-0910-02-4 Jointly organized by: University Utara Malaysia & Istanbul Zaim University
Uncontrolled Keywords:	Bayesian inference, Markov chain Monte Carlo (MCMC), heteroskedasticity, financial time series
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	School of Computing
Depositing User:	Mrs. Norazmilah Yaakub
Date Deposited:	12 Oct 2015 07:45
Last Modified:	27 Apr 2016 01:14
URI:	https://repo.uum.edu.my/id/eprint/15663

Actions (login required)

View Item