Markov switching dynamic multivariate garch models for hedging on foreign exchange market

• Main Authors: Pichayakone Rakpho, Woraphon Yamaka, Songsak Sriboonchitta
• Format: Book Series
• Published: 2019
• Subjects: Computer Science
• Online Access: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85065614375&origin=inward; http://cmuir.cmu.ac.th/jspui/handle/6653943832/65527
• Institution: Chiang Mai University

© Springer Nature Switzerland AG 2019. Foreign exchange rates is a significant factor affecting foreign transactions such as trade and investment. Foreign exchange rates, especially EUR/USD and GBP/USD, have a high fluctuation in recent years and lead a severe risk to investors. In this study, we consider a hedging strategy as a tool for offsetting the potential losses of investors. We introduce two classes of Markov Switching correlation model, namely MS-CCC-GARCH and MS-DCC-GARCH to compute the optimal hedge ratios and portfolio weights in the foreign exchange rates (EUR/USD and GBP/USD) for the period of 2013–2018. We also compare the performance of these two models with CCC-GARCH, DCC-GARCH models. The results show that MS-DCC-GARCH perform better for EUR/USD and GBP/USD spot and futures pairs. We finally complement our analysis by computing the dynamic hedge ratio and optimal portfolio weight, the result shows that the hedge ratios for both currencies are mostly remaining closely to 1 over the sample periods. However, we notice that, in some periods, the hedge ratios are particularly low in the low volatility market regime.