Forecasting value‐at‐risk in oil prices in the presence of volatility shifts

• Author: Farooq Malik,Bradley T. Ewing,Hassan Anjum
• DOI: http://doi.org/10.1002/rfe.1047
• Published date: 01 July 2019
• Date: 01 July 2019

Rev Financ Econ. 2019;37:341–350. wileyonlinelibrary.com/journal/rfe

|

341

© 2018 The University of New Orleans

1

|

INTRODUCTION

There is strong evidence that changes in oil prices have a significant effect on the financial markets and the overall economy.

Accurately measuring and forecasting this oil price risk can be extremely valuable especially in light of the high oil price

volatility observed over the last 20 years. There is robust evidence that financial markets are characterized by volatility shifts

(Starica & Granger, 2005). These volatility shifts produce an upward bias in estimated volatility persistence (Hillebrand, 2005)

and increase kurtosis which drives the observed non- normality in the data (Karoglou, 2010). Since models which forecast risk

are primarily concerned with extreme movements, it is essential that they account for these volatility shifts.

Value- at- Risk (VaR) is the primary tool used to forecast extreme declines in returns and is often used for designing optimal

risk management strategies. VaR is the expected loss in value of a portfolio that can occur with a specific probability over a

certain holding period. A VaR model which incorrectly forecasts the downside risk because it ignores volatility shifts present in

the data can have serious adverse consequences. Correctly forecasting major declines in oil prices can be extremely valuable for

corporations, investors and oil- exporting countries, so they can appropriately hedge against such risk. This issue is becoming

more important as markets are increasingly becoming more connected due to globalization.

While there are a few studies which have used different models to improve VaR forecasts to deal with the observed non-

normality and high volatility persistence of oil returns, we take an altogether different approach to address this problem.

Specifically, we explicitly incorporate the cause (i.e., volatility shifts) of the non- normality and high volatility persistence of

oil returns in the modeling process. Using a recent sample from October 1, 1997 to September 30, 2017 gives us additional

insight as it includes many extreme oil price movements. We endogenously detect volatility shifts using the modified iterated

cumulative sums of squares (ICSS) algorithm in daily oil returns. We show that incorporating volatility shifts into a standard

Received: 27 April 2018

|

Accepted: 21 July 2018

DOI: 10.1002/rfe.1047

ORIGINAL ARTICLE

Forecasting value- at- risk in oil prices in the presence of volatility

shifts

Bradley T. Ewing1

|

Farooq Malik2

|

Hassan Anjum3

1Rawls College of Business,Texas Tech

University, Lubbock, Texas

2College of Business,Zayed University,

Dubai, UAE

3Department of Economics,Texas Tech

University, Lubbock, Texas

Correspondence

Farooq Malik, College of Business, Zayed

University, Dubai, UAE.

Email: farooq.malik@zu.ac.ae.

Funding information

Zayed University

Abstract

Recent evidence suggests shifts (structural breaks) in the volatility of returns causes

non- normality by significantly increasing kurtosis. In this paper, we endogenously

detect significant shifts in the volatility of oil prices and incorporate this information

to estimate Value- at- Risk (VaR) to accurately forecast large declines in oil prices.

Our out- of- sample performance results indicate that the model, which incorporates

both time varying volatility (without making any distributional assumptions) and

shifts in volatility, produces more accurate VaR forecasts than several benchmark

methods. We make a timely contribution as the recent more frequent occurrences of

unexpected large oil price declines has gained significant attention because of its

substantial impact on the financial markets and the global economy.

JEL CLASSIFICATION

G1

KEYWORDS

GARCH, oil volatility, structural breaks