Abstract
Forecasting volatility is of great importance an important topic for researchers, entrepreneurs, and policymakers. This work compares different volatility models to ascertain their forecasting efficiency. The models include standard approaches such as Autoregressive Conditional Heteroskedasticity (GARCH), exponential GARCH, and Stochastic Volatility models (SV). For estimation, a comparison between the Frequentist and the Bayesian approaches are made using the maximum likelihood and the Monte Carlo Markov Chains (MCMC) methods. The case analysis considers the Mexican peso/US dollar exchange rate. The results show a favorable behavior between the SV models estimated with the MCMC and the GARCH models in forecasting out of the sample. Additionally, the analysis shows that the current volatility reacts to the data within the last period, despite the former periods.
Highlights
Exchange rates play an important role in international trade, the determination of investments, business risk management, as well as in the economic situation within a country (Frankel and Saravelos, 2012; Korol 2014)
The exchange rate is a financial variable difficult to predict due to the different inaccuracies that may occur over time
General Autoregressive Conditional Heteroskedasticity (GARCH) and Stochastic Volatility models (SV) models have been commonly used for forecasting and estimating volatility
Summary
Exchange rates play an important role in international trade, the determination of investments, business risk management, as well as in the economic situation within a country (Frankel and Saravelos, 2012; Korol 2014). High volatility generates a decrease in yields and significant losses for economic agents (Guo et al 2014; Bali and Zhou, 2016; Morales et al 2016) In this regard, some studies are oriented to know both the causes of these fluctuations and the alternatives to minimize uncertainty (Korol, 2014; Gupta and Kashyap, 2016; Lahmiri, 2017). Most of the research efforts regarding price variability have focused on standard forecast models, where volatility is a key parameter, using conditional heteroskedasticity dependent on time (Korol, 2014; Pinho et al 2016) This type of volatility models is called General Autoregressive Conditional Heteroskedasticity (GARCH), proposed by Engle (1982) and generalized by Bollerslev (1986) as an alternative to model non-linearity and volatility clusters in a simple way and adapting to different scenarios.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have