Volatility forecasting of exchange rate by quantile regression ☆ Alex YiHou Huang a, ⁎, Sheng-Pen Peng b , Fangjhy Li c , Ching-Jie Ke a a College of Management, Yuan Ze University, Taiwan b Department of Real Estate Management, Hsing Kuo University of Management, Taiwan c Department of Finance, Hsing Kuo University of Management, Taiwan article info abstract Article history: Received 11 October 2009 Received in revised form 7 July 2010 Accepted 18 October 2010 Available online 31 January 2011 Exchange rates are known to have irregular return patterns; not only their return volatilities but the distribution functions themselves vary with time. Quantile regression allows one to predict the volatility of time series without assuming an explicit form for the underlying distribution. This study presents an approach to exchange rate volatility forecasting by quantile regression utilizing a uniformly spaced series of estimated quantiles. Based on empirical evidence of nine exchange rate series, using 19 years of daily data, the adopted approach generally produces more reliable volatility forecasts than other key methods. © 2011 Elsevier Inc. All rights reserved. JEL classification: C53 E27 G17 Keywords: Exchange rate Volatility Quantile regression 1. Introduction Volatility forecasting has been a key research subject in financial economics for the past few decades. Volatility can be interpreted as the level of uncertainty in a financial asset, and is applicable to many risk management processes. It is also a critical input variable in pricing financial derivatives and plays a central role in investment decisions. Malik and Hammoudeh (2007) and Gutierrez, Martinez, and Tse (2009) documented that financial volatility can be transmitted across assets and global markets. Consequently, better understanding and measurement of volatility for key macroeconomic and international financial variables can significantly benefit management of financial risks. Exchange rate volatility, in particular, has also been a major research subject. Prior studies show a significant negative relationship between exchange rate volatility and international trade as trading firms are risk averse (Arize, Osang, & Slottje, 2000; Arize, Osang, & Slottje, 2008; Choudhry, 2005; De Vita & Abbott, 2004; Fang, Lai, & Miller, 2009; Hooper & Kohlhagen, 1978). Government and central bank interventions have been documented as a key factor affecting exchange rate volatility (Beine, Benassy-Quere, & Lecourt, 2002; Frenkel, Pierdzioch, & Stadtmann, 2005; Sideris, 2008). Exchange rate volatility is proved to have impacts on macroeconomic conditions such as aggregate supply shocks (Hau, 2002), inflation volatility (Gonzaga & Terra, 1997), and distribution costs for consumer goods (Burstein, Neves, & Rebelo, 2003). Significant interdependences are also documented between exchange rate volatility and economic performances including firm's profitability (Baum, Caglayan, & Barkoulas 2001), International Review of Economics and Finance 20 (2011) 591–606 ☆ The authors thank two anonymous referees and editor Carl Chen for insightful suggestions which constructively improve the article. This paper is also benefited from valuable comments of participants in the 5th International Conference on Asian Financial Markets, Nagasaki, Japan and the 22nd Australasian Finance and Banking Conference, Sydney, Australia. The authors thank Wen-Cheng Hu, Chih-Chun Chen, and Guo-An Li for their excellent research assistance. Huang thanks the support from the National Science Council of Taiwan (NSC96-2415-H-155-001). ⁎ Corresponding author and assistant professor of finance at: 135 Yuan-Tung Road, Chung-Li, Taoyuan 32002, Taiwan, ROC. Tel.: +886 3 4638800x2668; fax: +886 3 4354624. E-mail address: huang@saturn.yzu.edu.tw (A.Y. Huang). 1059-0560/$ – see front matter © 2011 Elsevier Inc. All rights reserved. doi:10.1016/j.iref.2011.01.005 Contents lists available at ScienceDirect International Review of Economics and Finance journal homepage: www.elsevier.com/locate/iref