A comparison of conditional predictive ability of implied volatility and realized measures in forecasting volatility

• Author: Tingting Ying,Yanlong Shi,Chunrong Ai,Yafeng Shi
• Date: 01 November 2020
• Published date: 01 November 2020
• DOI: http://doi.org/10.1002/for.2666

Received: 22 October 2019 Accepted: 12 January 2020

DOI: 10.1002/for.2666

RESEARCH ARTICLE

A comparison of conditional predictive ability of implied

volatility and realized measures in forecasting volatility

Yafeng Shi1Tingting Ying2Yanlong Shi3Chunrong Ai4

1School of Science, Ningbo University of

Technology,Zhejiang Province, Ningbo,

PR, China

2Faculty of Business, University of

Nottingham, Ningbo, China

3Zhejiang Pharmaceutical College,

Zhejiang Province, Ningbo, PR, China

4Institute for Advanced studies in Finance

and Economics, Hubei University of

Economics, Hubei Province, Wuhan, PR,

China

Correspondence

Ai Chunrong, Institute for Advanced

studies in Finance and Economics, Hubei

University of Economics, Wuhan, Hubei

Province, 430205, PR China.

Email: chunrongai@hotmail.com

Funding information

National Statistical Science Research

Program, Grant/AwardNumber:

2019LY71; MOE (Ministry of Education in

China) Liberal arts and Social Sciences

Foundation, Grant/AwardNumber:

20YJC790111; Natural Science Foundation

of Ningbo project, Grant/AwardNumber:

2018A610130; National Natural Science

Foundation of China project,

Grant/AwardNumber: 71873138; Ningbo

Soft Science Foundation, Grant/Award

Number: 2017A10113

Abstract

In a conditional predictive ability test framework,we investigate whether market

factors influence the relative conditional predictive ability of realized measures

(RMs) and implied volatility (IV), which is able to examine the asynchronism in

their forecasting accuracy, and further analyze their unconditional forecasting

performance for volatility forecast. Our results show that the asynchronism can

be detected significantly and is strongly related to certain market factors, and

the comparison between RMs and IV on average forecast performance is more

efficient than previous studies. Finally,we use the factors to extend the empirical

similarity (ES) approach for combination of forecasts derived from RMs and IV.

KEYWORDS

conditional predictive ability,forecasting competitions, implied volatility, realized volatility, volatil-

ity forecasts

1INTRODUCTION

Employing accurate volatility forecasts is highly important

for many financial market practitioners and regulators.

Future volatility can be forecast using historical infor-

mation extracted from different frequencies data, and/or

the information provided by option prices. The literature

comparing the volatility forecasts of realized measures

(RMs) and implied volatility (IV) has been rapidly grow-

ing. For example, early empirical studies (Beckers, 1981;

Chiras & Manaster, 1978; Latané & Rendleman, 1976)

indicate that IV can be regarded as a good predictor of

future volatility. Since option traders have other infor-

mation about future events that may be relevant, IV is

often referred to as the market's volatility forecast and is

indicative of a forward-looking forecast. As nonparamet-

ric daily RMs of volatility constructed from high-frequency

data have become prevalent, the focus of the research

has shifted to comparing the predictive power of IV with

Journal of Forecasting. 2020;39:1025–1034. wileyonlinelibrary.com/journal/for © 2020 John Wiley & Sons, Ltd. 1025