Journal Of Empirical Finance 19 (2012) 627–639

Journal of Empirical Finance 19 (2012) 627–639

Contents lists available at SciVerse ScienceDirect

Journal of Empirical Finance
journal homepage: www.elsevier.com/locate/jempfin

Forecasting exchange rate volatility: The superior performance of
conditional combinations of time series and option implied forecasts☆
Guillermo Benavides a,⁎, Carlos Capistrán b
a
b

Banco de México,Mexico
Bank of America Merrill Lynch, Mexico

article

info

Article history:
Received 26 February 2010
Accepted 5 July 2012
Available online 16 July 2012
Keywords:
Composite forecasts
Forecast evaluation
GARCH
Implied volatility
Mexican peso–U.S. dollar exchange rate
Regime switching

abstract
This paper provides empirical evidence that combinations of option implied and timeseries
volatility forecasts that are conditional on current information are statistically superior to
individual models, unconditional combinations, and hybrid forecasts. Superior forecasting
performance is achieved by both, taking into account the conditional expected performance of
each model given current information, and combining individual forecasts. The method used
in this paper to produceconditional combinations extends the application of conditional
predictive ability tests to select forecast combinations. The application is for volatility forecasts
of the Mexican peso–US dollar exchange rate, where realized volatility calculated using
intraday data is used as a proxy for the (latent) daily volatility.
© 2012 Elsevier B.V. All rights reserved.

JEL classification:
C22C52
C53
G10

1. Introduction
Even though several models are widely used by academics and practitioners to forecast volatility, nowadays there is no consensus
about which method is superior in terms of forecasting accuracy (Andersen et al., 2006; Poon and Granger, 2003; Taylor, 2005). The
vast majority of models can be classified in two classes: models based on time series, and models based onoptions.
There are basically two classes of models used in volatility forecasting: models based on time series, and models based on options
(Poon and Granger, 2003). Among the time series models, there are models based on past volatility, such as historical averages of

☆ We thank Alejandro Díaz de León, Antonio E. Noriega, Carla Ysusi, Carlos Muñoz Hink, the Editor and seminar participantsat the 2008 Latin American
Meeting of the Econometric Society at Rio de Janeiro, the XII Meeting of CEMLA's Central Bank Researchers' Network at Banco de España, the 2008 Meeting of the
Society of Nonlinear Dynamics and Econometrics at the Federal Reserve Bank of San Francisco, Banco de México, ITAM, ITESM Campus Cd. de México, and
Universidad del Valle de México for helpful comments. We alsothank Antonio Sibaja and Pablo Bravo for helping us with the exchange rate intraday data. Andrea
San Martín, Gabriel López-Moctezuma, Luis Adrián Muñiz, and Sergio Vargas provided excellent research assistance. The final draft of this paper was written
while Carlos Capistrán was working at Banco de México (Central Bank of Mexico). The opinions expressed in this article are solely those of theauthors and do not
necessarily reflect the views of Banco de México or Bank of America Merrill Lynch.
⁎ Corresponding author at: Av 5 de Mayo # 2, Centro, México, D.F., CP. 06059, México. Tel.: +52 55 5237 2000x3877; fax: +52 55 5237 2559.
E-mail address: gbenavid@banxico.org.mx (G. Benavides).
0927-5398/$ – see front matter © 2012 Elsevier B.V. All rights reserved.
doi:10.1016/j.jempfin.2012.07.001628

G. Benavides, C. Capistrán / Journal of Empirical Finance 19 (2012) 627–639

squared price returns, Autoregressive Conditional Heteroskedasticity-type models (ARCH-Type), such as ARCH, GARCH, and EGARCH,
and stochastic volatility models.1 Among the options based volatility models, typically called option implied volatilities (IV), there are
the Black–Scholes-type models (Black...