Out‐of‐sample volatility prediction: A new mixed‐frequency approach

• Author: Feng Ma,Tianyi Wang,Yaojie Zhang,Li Liu
• Published date: 01 November 2019
• DOI: http://doi.org/10.1002/for.2590
• Date: 01 November 2019

RESEARCH ARTICLE

Out‐of‐sample volatility prediction: A new mixed‐frequency

approach

Yaojie Zhang

1

| Feng Ma

2

| Tianyi Wang

3

| Li Liu

4

1

School of Economics and Management,

Nanjing University of Science and

Technology, Nanjing, China

2

School of Economics and Management,

Southwest Jiaotong University, Chengdu,

China

3

School of Banking and Finance,

University of International Business and

Economics, Beijing, China

4

School of Finance, Nanjing Audit

University, Nanjing, China

Correspondence

Feng Ma, School of Economics and

Management, Southwest Jiaotong

University, No. 111, North 1st Section, 2nd

Ring Road, Chengdu, 610031, China

Email: mafeng2016@swjtu.edu.cn

Abstract

This paper proposes a new mixed‐frequency approach to predict stock return

volatilities out‐of‐sample. Based on the strategy of momentum of predictability

(MoP), our mixed‐frequency approach has a model switching mechanism that

switches between generalized autoregressive conditional heteroskedasticity

(GARCH)‐class models that only use low‐frequency data and heterogeneous

autoregressive models of realized volatility (HAR‐RV)‐type that only use

high‐frequency data. The MoP model simply selects a forecast with relatively

good past performance between the GARCH‐class and HAR‐RV‐type forecasts.

The model confidence set (MCS) test shows that our MoP strategy significantly

outperforms the competing models, which is robust to various settings. The

MoP test shows that a relatively good recent past forecasting performance of

the GARCH‐class or HAR‐RV‐type model is significantly associated with a rel-

atively good current performance, supporting the success of the MoP model.

Highlights

1. This paper proposes a new mixed‐frequency approach to predict volatilities.

2. Our mixed‐frequency approach is based on the momentum of predictability

(MoP).

3. Our MoP model has a model switching mechanism.

4. The MoP model significantly outperforms the competing models out‐of‐

sample.

5. We demonstrate the existence of MoP between the GARCH‐class and HAR‐

RV‐type models.

KEYWORDS

mixed frequency, model switching, momentum of predictability,out‐of‐sample prediction, volatility

1|INTRODUCTION

Stock return volatility is central to asset allocation, asset

pricing, and risk management. Forecasting volatilities is

thus of great interest to both academics and practitioners.

In the last century, generalized autoregressive conditional

heteroskedasticity (GARCH)‐class models are the most

prevailing models for volatility prediction. The represen-

tative models include GARCH (Bollerslev, 1986), expo-

nential GARCH (EGARCH; Nelson, 1991), Glosten–

Jagannathan–Runkle (GJR; Glosten, Jagannathan, &

Runkle, 1993), fractionally integrated GARCH

Received: 30 October 2018 Accepted: 11 March 2019

DOI: 10.1002/for.2590

Journal of Forecasting. 2019; :669–680. © 2019 John Wiley & Sons, Ltd.wileyonlinelibrary.com/journal/for

669

38