The Bias in Time-Series Volatility Forecasts

Journal of Futures Markets, 2009

28 Pages Posted: 17 May 2009  

Louis H. Ederington

University of Oklahoma - Division of Finance

Wei Guan

University of South Florida St. Petersburg

Multiple version iconThere are 2 versions of this paper

Date Written: May 17, 2009

Abstract

By Jensen’s inequality, a model’s forecasts of the variance and standard deviation of returns cannot both be unbiased. This paper explores the bias in GARCH type model forecasts of the standard deviation of returns, which we argue is the more appropriate volatility measure for most financial applications. For a wide variety of markets, the GARCH, EGARCH, and GJR (or TGARCH) models tend to persistently over-estimate the standard deviation of returns while the ARLS model of Ederington and Guan (2005, JFM) does not. Furthermore, the GARCH and GJR forecasts are especially biased following high volatility days which cause a large jump in forecast volatility which is rarely fully realized.

Keywords: GARCH, EGARCH, volatility, value-at-risk

JEL Classification: G123, C22, C53

Suggested Citation

Ederington, Louis H. and Guan, Wei, The Bias in Time-Series Volatility Forecasts (May 17, 2009). Journal of Futures Markets, 2009. Available at SSRN: https://ssrn.com/abstract=1406172

Louis H. Ederington (Contact Author)

University of Oklahoma - Division of Finance ( email )

Norman, OK 73019
United States
405-325-5591 (Phone)
405-325-7688 (Fax)

Wei Guan

University of South Florida St. Petersburg ( email )

College of Business
140 Seventh Avenue South
St. Petersburg, FL 33701-5016
United States
(727) 873-4945 (Phone)
(727) 873-4192 (Fax)

Paper statistics

Downloads
113
Rank
103,741
Abstract Views
595