Volatility forecasts using stochastic volatility models with nonlinear leverage effects

Kenichiro McAlinn, Asahi Ushio, Teruo Nakatsuma

Research output: Contribution to journalArticle

Abstract

The leverage effect—the correlation between an asset's return and its volatility—has played a key role in forecasting and understanding volatility and risk. While it is a long standing consensus that leverage effects exist and improve forecasts, empirical evidence puzzlingly does not show that this effect exists for many individual stocks, mischaracterizing risk, and therefore leading to poor predictive performance. We examine this puzzle, with the goal to improve density forecasts, by relaxing the assumption of linearity of the leverage effect. Nonlinear generalizations of the leverage effect are proposed within the Bayesian stochastic volatility framework in order to capture flexible leverage structures. Efficient Bayesian sequential computation is developed and implemented to estimate this effect in a practical, on-line manner. Examining 615 stocks that comprise the S&P500 and Nikkei 225, we find that our proposed nonlinear leverage effect model improves predictive performances for 89% of all stocks compared to the conventional stochastic volatility model.

Original languageEnglish
JournalJournal of Forecasting
DOIs
Publication statusAccepted/In press - 2019 Jan 1

Fingerprint

Leverage Effect
Stochastic Volatility Model
Nonlinear Effects
Stochastic models
Volatility
Forecast
Flexible structures
Leverage
Stochastic Volatility
Linearity
Forecasting
Leverage effect
Volatility forecasts
Stochastic volatility model
Estimate

Keywords

  • Bayesian analysis
  • leverage effect
  • particle learning
  • stochastic volatility
  • volatility forecasting

ASJC Scopus subject areas

  • Modelling and Simulation
  • Computer Science Applications
  • Strategy and Management
  • Statistics, Probability and Uncertainty
  • Management Science and Operations Research

Cite this

Volatility forecasts using stochastic volatility models with nonlinear leverage effects. / McAlinn, Kenichiro; Ushio, Asahi; Nakatsuma, Teruo.

In: Journal of Forecasting, 01.01.2019.

Research output: Contribution to journalArticle

@article{656c5cc2f1094d399723bf4ed47485c7,
title = "Volatility forecasts using stochastic volatility models with nonlinear leverage effects",
abstract = "The leverage effect—the correlation between an asset's return and its volatility—has played a key role in forecasting and understanding volatility and risk. While it is a long standing consensus that leverage effects exist and improve forecasts, empirical evidence puzzlingly does not show that this effect exists for many individual stocks, mischaracterizing risk, and therefore leading to poor predictive performance. We examine this puzzle, with the goal to improve density forecasts, by relaxing the assumption of linearity of the leverage effect. Nonlinear generalizations of the leverage effect are proposed within the Bayesian stochastic volatility framework in order to capture flexible leverage structures. Efficient Bayesian sequential computation is developed and implemented to estimate this effect in a practical, on-line manner. Examining 615 stocks that comprise the S&P500 and Nikkei 225, we find that our proposed nonlinear leverage effect model improves predictive performances for 89{\%} of all stocks compared to the conventional stochastic volatility model.",
keywords = "Bayesian analysis, leverage effect, particle learning, stochastic volatility, volatility forecasting",
author = "Kenichiro McAlinn and Asahi Ushio and Teruo Nakatsuma",
year = "2019",
month = "1",
day = "1",
doi = "10.1002/for.2618",
language = "English",
journal = "Journal of Forecasting",
issn = "0277-6693",
publisher = "John Wiley and Sons Ltd",

}

TY - JOUR

T1 - Volatility forecasts using stochastic volatility models with nonlinear leverage effects

AU - McAlinn, Kenichiro

AU - Ushio, Asahi

AU - Nakatsuma, Teruo

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The leverage effect—the correlation between an asset's return and its volatility—has played a key role in forecasting and understanding volatility and risk. While it is a long standing consensus that leverage effects exist and improve forecasts, empirical evidence puzzlingly does not show that this effect exists for many individual stocks, mischaracterizing risk, and therefore leading to poor predictive performance. We examine this puzzle, with the goal to improve density forecasts, by relaxing the assumption of linearity of the leverage effect. Nonlinear generalizations of the leverage effect are proposed within the Bayesian stochastic volatility framework in order to capture flexible leverage structures. Efficient Bayesian sequential computation is developed and implemented to estimate this effect in a practical, on-line manner. Examining 615 stocks that comprise the S&P500 and Nikkei 225, we find that our proposed nonlinear leverage effect model improves predictive performances for 89% of all stocks compared to the conventional stochastic volatility model.

AB - The leverage effect—the correlation between an asset's return and its volatility—has played a key role in forecasting and understanding volatility and risk. While it is a long standing consensus that leverage effects exist and improve forecasts, empirical evidence puzzlingly does not show that this effect exists for many individual stocks, mischaracterizing risk, and therefore leading to poor predictive performance. We examine this puzzle, with the goal to improve density forecasts, by relaxing the assumption of linearity of the leverage effect. Nonlinear generalizations of the leverage effect are proposed within the Bayesian stochastic volatility framework in order to capture flexible leverage structures. Efficient Bayesian sequential computation is developed and implemented to estimate this effect in a practical, on-line manner. Examining 615 stocks that comprise the S&P500 and Nikkei 225, we find that our proposed nonlinear leverage effect model improves predictive performances for 89% of all stocks compared to the conventional stochastic volatility model.

KW - Bayesian analysis

KW - leverage effect

KW - particle learning

KW - stochastic volatility

KW - volatility forecasting

UR - http://www.scopus.com/inward/record.url?scp=85070735527&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070735527&partnerID=8YFLogxK

U2 - 10.1002/for.2618

DO - 10.1002/for.2618

M3 - Article

JO - Journal of Forecasting

JF - Journal of Forecasting

SN - 0277-6693

ER -